Pattern Prediction System

============================================

Import Libraries

import os
import glob
import time
import math
import numpy as np
import pandas as pd
import tensorflow as tf
import matplotlib.pyplot as plt

from keras.layers import LSTM
from keras.layers import Dense
from keras.layers import Flatten
from keras.models import Sequential
from prettytable import PrettyTable  
from keras.layers import Bidirectional
from tensorflow.keras.layers import GRU
from astropy.table import Table, Column
from keras.layers import TimeDistributed
from keras.layers.convolutional import Conv1D
from sklearn.metrics import mean_squared_error
from sklearn.preprocessing import MinMaxScaler
from keras.layers.convolutional import MaxPooling1D
from tensorflow.keras.layers import SimpleRNN as RNN

!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

Approach 1 - Single Training

!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

Load Dataset

path = ('Datasets/Single Dataset')
data = [os.path.join(dp, f) for dp, dn, filenames in os.walk(path) for f in filenames if os.path.splitext(f)[1] == '.csv']

print("\n\nName of Datasets that are Used:")
print("===============================\n\n")
for i in data:
    print(i)

Name of Datasets that are Used:
===============================


Datasets/Single Dataset\Hig-DR\node_15.csv
Datasets/Single Dataset\Hig-DR\node_24.csv
Datasets/Single Dataset\Hig-DR\node_33.csv
Datasets/Single Dataset\Hig-DR\node_48.csv
Datasets/Single Dataset\Hig-DR\node_7.csv
Datasets/Single Dataset\Low-DR\node_15.csv
Datasets/Single Dataset\Low-DR\node_24.csv
Datasets/Single Dataset\Low-DR\node_33.csv
Datasets/Single Dataset\Low-DR\node_48.csv
Datasets/Single Dataset\Low-DR\node_7.csv
Datasets/Single Dataset\Med-DR\node_15.csv
Datasets/Single Dataset\Med-DR\node_24.csv
Datasets/Single Dataset\Med-DR\node_33.csv
Datasets/Single Dataset\Med-DR\node_48.csv
Datasets/Single Dataset\Med-DR\node_7.csv

all_data_node_7_training = pd.DataFrame()
all_data_node_15_training = pd.DataFrame()
all_data_node_24_training = pd.DataFrame()
all_data_node_33_training = pd.DataFrame()
all_data_node_48_training = pd.DataFrame()

all_data_node_7_testing = pd.DataFrame()
all_data_node_15_testing = pd.DataFrame()
all_data_node_24_testing = pd.DataFrame()
all_data_node_33_testing = pd.DataFrame()
all_data_node_48_testing = pd.DataFrame()

for i in data:
    sample_data = pd .read_csv(i)
    
    if("node_7" in i):
        all_data_node_7_training = all_data_node_7_training.append(sample_data.head(650))
        all_data_node_7_testing = all_data_node_7_testing.append(sample_data[651:])
    
    if("node_15" in i):
        all_data_node_15_training = all_data_node_15_training.append(sample_data.head(650))
        all_data_node_15_testing = all_data_node_15_testing.append(sample_data[651:])
        
    if("node_24" in i):
        all_data_node_24_training = all_data_node_24_training.append(sample_data.head(650))
        all_data_node_24_testing = all_data_node_24_testing.append(sample_data[651:])
    
    if("node_33" in i):
        all_data_node_33_training = all_data_node_33_training.append(sample_data.head(650))
        all_data_node_33_testing = all_data_node_33_testing.append(sample_data[651:])
        
    if("node_48" in i):
        all_data_node_48_training = all_data_node_48_training.append(sample_data.head(650))
        all_data_node_48_testing = all_data_node_48_testing.append(sample_data[651:])

all_data_node_7_training = all_data_node_7_training.drop("Time", axis = 1)
all_data_node_7_training = all_data_node_7_training.drop("Node", axis = 1)
all_data_node_7_training.reset_index(drop=True, inplace=True)

all_data_node_15_training = all_data_node_15_training.drop("Time", axis = 1)
all_data_node_15_training = all_data_node_15_training.drop("Node", axis = 1)
all_data_node_15_training.reset_index(drop=True, inplace=True)

all_data_node_24_training = all_data_node_24_training.drop("Time", axis = 1)
all_data_node_24_training = all_data_node_24_training.drop("Node", axis = 1)
all_data_node_24_training.reset_index(drop=True, inplace=True)

all_data_node_33_training = all_data_node_33_training.drop("Time", axis = 1)
all_data_node_33_training = all_data_node_33_training.drop("Node", axis = 1)
all_data_node_33_training.reset_index(drop=True, inplace=True)

all_data_node_48_training = all_data_node_48_training.drop("Time", axis = 1)
all_data_node_48_training = all_data_node_48_training.drop("Node", axis = 1)
all_data_node_48_training.reset_index(drop=True, inplace=True)


all_data_node_7_testing = all_data_node_7_testing.drop("Time", axis = 1)
all_data_node_7_testing = all_data_node_7_testing.drop("Node", axis = 1)
all_data_node_7_testing.reset_index(drop=True, inplace=True)

all_data_node_15_testing = all_data_node_15_testing.drop("Time", axis = 1)
all_data_node_15_testing = all_data_node_15_testing.drop("Node", axis = 1)
all_data_node_15_testing.reset_index(drop=True, inplace=True)

all_data_node_24_testing = all_data_node_24_testing.drop("Time", axis = 1)
all_data_node_24_testing = all_data_node_24_testing.drop("Node", axis = 1)
all_data_node_24_testing.reset_index(drop=True, inplace=True)

all_data_node_33_testing = all_data_node_33_testing.drop("Time", axis = 1)
all_data_node_33_testing = all_data_node_33_testing.drop("Node", axis = 1)
all_data_node_33_testing.reset_index(drop=True, inplace=True)

all_data_node_48_testing = all_data_node_48_testing.drop("Time", axis = 1)
all_data_node_48_testing = all_data_node_48_testing.drop("Node", axis = 1)
all_data_node_48_testing.reset_index(drop=True, inplace=True)

print("\n\nMain Datasets of Node 7 that is Used:")
print("=====================================\n\n")
print("Training Data:\n\n")
print(all_data_node_7_training)
print("\n\nTesting Data:\n\n")
print(all_data_node_7_testing)

print("\n\nMain Datasets of Node 15 that is Used:")
print("=====================================\n\n")
print("Training Data:\n\n")
print(all_data_node_15_training)
print("\n\nTesting Data:\n\n")
print(all_data_node_15_testing)

print("\n\nMain Datasets of Node 24 that is Used:")
print("=====================================\n\n")
print("Training Data:\n\n")
print(all_data_node_24_training)
print("\n\nTesting Data:\n\n")
print(all_data_node_24_testing)

print("\n\nMain Datasets of Node 33 that is Used:")
print("=====================================\n\n")
print("Training Data:\n\n")
print(all_data_node_33_training)
print("\n\nTesting Data:\n\n")
print(all_data_node_33_testing)

print("\n\nMain Datasets of Node 48 that is Used:")
print("=====================================\n\n")
print("Training Data:\n\n")
print(all_data_node_48_training)
print("\n\nTesting Data:\n\n")
print(all_data_node_48_testing)

Main Datasets of Node 7 that is Used:
=====================================


Training Data:


         pos_x    pos_y     speed       energy
0      71.1322  124.511  0.000000  1118.321423
1      71.7625  125.454  2.949013  1117.330000
2      72.7025  126.861  2.949013  1116.338577
3      73.6426  128.268  2.949013  1115.347154
4      74.5826  129.675  2.949013  1114.355731
...        ...      ...       ...          ...
1945  255.3640  120.883  0.000000     0.000000
1946  255.3640  120.883  0.000000     0.000000
1947  255.3640  120.883  0.000000     0.000000
1948  255.3640  120.883  0.000000     0.000000
1949  255.3640  120.883  0.000000     0.000000

[1950 rows x 4 columns]


Testing Data:


       pos_x    pos_y     speed     energy
0    158.247  254.898  7.842828  210.08317
1    159.187  256.305  7.842828  202.52120
2    160.127  257.712  7.842828  194.95923
3    161.067  259.119  7.842828  187.39726
4    162.007  260.526  7.842828  179.83529
..       ...      ...       ...        ...
295  255.364  120.883  0.000000    0.00000
296  255.364  120.883  0.000000    0.00000
297  255.364  120.883  0.000000    0.00000
298  255.364  120.883  0.000000    0.00000
299  255.364  120.883  0.000000    0.00000

[300 rows x 4 columns]


Main Datasets of Node 15 that is Used:
=====================================


Training Data:


         pos_x    pos_y     speed      energy
0      87.0349  185.017  0.000000  751.723821
1      87.6682  185.454  4.969239  747.060000
2      89.1959  186.473  4.969239  742.396179
3      90.7237  187.492  4.969239  737.732359
4      92.2515  188.511  4.969239  733.068538
...        ...      ...       ...         ...
1945  257.2610  229.576  0.000000    0.000000
1946  257.2610  229.576  0.000000    0.000000
1947  257.2610  229.576  0.000000    0.000000
1948  257.2610  229.576  0.000000    0.000000
1949  257.2610  229.576  0.000000    0.000000

[1950 rows x 4 columns]


Testing Data:


       pos_x    pos_y  speed  energy
0    171.695  241.496    0.0     0.0
1    171.695  241.496    0.0     0.0
2    171.695  241.496    0.0     0.0
3    171.695  241.496    0.0     0.0
4    171.695  241.496    0.0     0.0
..       ...      ...    ...     ...
295  257.261  229.576    0.0     0.0
296  257.261  229.576    0.0     0.0
297  257.261  229.576    0.0     0.0
298  257.261  229.576    0.0     0.0
299  257.261  229.576    0.0     0.0

[300 rows x 4 columns]


Main Datasets of Node 24 that is Used:
=====================================


Training Data:


        pos_x    pos_y     speed       energy
0     368.653  91.6318  0.000000  2137.551711
1     368.548  90.8244  0.370118  2137.110000
2     368.392  89.6361  0.370118  2136.668289
3     368.237  88.4477  0.370118  2136.226578
4     368.082  87.2593  0.370118  2135.784867
...       ...      ...       ...          ...
1945  381.943  69.8461  2.405508  1787.561232
1946  382.406  70.5222  2.405508  1786.899060
1947  382.869  71.1982  2.405508  1786.236888
1948  383.332  71.8743  2.405508  1785.574716
1949  383.794  72.5503  2.405508  1784.912544

[1950 rows x 4 columns]


Testing Data:


       pos_x    pos_y     speed       energy
0    384.720  73.9024  2.405508   775.181610
1    385.183  74.5785  2.405508   773.047275
2    385.646  75.2545  2.405508   770.912940
3    386.109  75.9306  2.405508   768.778605
4    386.572  76.6066  2.405508   766.644270
..       ...      ...       ...          ...
295  382.406  70.5222  7.435760  1467.316100
296  382.869  71.1982  7.435760  1463.320168
297  383.332  71.8743  7.435760  1459.324236
298  383.794  72.5503  7.435760  1455.328304
299  384.257  73.2264  7.435760  1451.332372

[300 rows x 4 columns]


Main Datasets of Node 33 that is Used:
=====================================


Training Data:


        pos_x    pos_y     speed       energy
0     122.157  322.683  0.000000  1617.216083
1     122.299  322.767  3.404496  1615.083000
2     123.672  322.697  3.404496  1612.949917
3     125.045  322.628  3.404496  1610.816834
4     126.418  322.558  3.404496  1608.683751
...       ...      ...       ...          ...
1945  376.262  192.742  3.466386   381.543423
1946  377.419  194.029  3.466386   381.205052
1947  378.576  195.316  3.466386   380.866681
1948  379.733  196.603  3.466386   380.528310
1949  380.890  197.890  3.466386   380.189939

[1950 rows x 4 columns]


Testing Data:


       pos_x    pos_y     speed      energy
0    248.615  316.373  1.463984  228.579050
1    249.988  316.303  1.463984  226.445967
2    251.361  316.234  1.463984  224.312884
3    252.734  316.164  1.463984  222.179801
4    254.107  316.095  1.463984  220.046718
..       ...      ...       ...         ...
295  377.419  194.029  6.626459  347.367962
296  378.576  195.316  6.626459  347.029591
297  379.733  196.603  6.626459  346.691220
298  380.890  197.890  6.626459  346.352849
299  382.047  199.177  6.626459  346.014478

[300 rows x 4 columns]


Main Datasets of Node 48 that is Used:
=====================================


Training Data:


        pos_x    pos_y     speed       energy
0     369.390  151.479  0.000000  2998.925928
1     369.468  151.490  2.057354  2998.120000
2     369.728  151.527  2.057354  2996.240000
3     369.989  151.564  2.057354  2994.360000
4     370.250  151.602  2.057354  2992.480000
...       ...      ...       ...          ...
1945  391.898  154.707  5.970805   779.237960
1946  392.159  154.745  5.970805   777.880550
1947  392.420  154.782  5.970805   776.523140
1948  392.681  154.820  5.970805   775.165730
1949  392.941  154.857  5.970805   773.808320

[1950 rows x 4 columns]


Testing Data:


       pos_x    pos_y     speed      energy
0    393.463  154.932  5.970805  903.785894
1    393.724  154.969  5.970805  898.273815
2    393.985  155.007  5.970805  892.761735
3    394.246  155.044  5.970805  887.249655
4    394.506  155.082  5.970805  881.737575
..       ...      ...       ...         ...
295  392.159  154.745  7.440762  493.946780
296  392.420  154.782  7.440762  488.584160
297  392.681  154.820  7.440762  483.221540
298  392.941  154.857  7.440762  477.858920
299  393.202  154.894  7.440762  472.496300

[300 rows x 4 columns]

Visual Representation of 5 Nodes

plt.figure()
fig = plt.gcf()
fig.set_size_inches(14, 5)
plt.plot(all_data_node_7_training["pos_x"])
plt.plot(all_data_node_15_training["pos_x"])
plt.plot(all_data_node_24_training["pos_x"])
plt.plot(all_data_node_33_training["pos_x"])
plt.plot(all_data_node_48_training["pos_x"])
plt.legend(['Node 7','Node 15','Node 24','Node 33','Node 48'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.title('pos_x')
plt.grid(True)
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(14, 5)
plt.plot(all_data_node_7_training["pos_y"])
plt.plot(all_data_node_15_training["pos_y"])
plt.plot(all_data_node_24_training["pos_y"])
plt.plot(all_data_node_33_training["pos_y"])
plt.plot(all_data_node_48_training["pos_y"])
plt.legend(['Node 7','Node 15','Node 24','Node 33','Node 48'], loc='upper right')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(14, 5)
plt.plot(all_data_node_7_training["energy"])
plt.plot(all_data_node_15_training["energy"])
plt.plot(all_data_node_24_training["energy"])
plt.plot(all_data_node_33_training["energy"])
plt.plot(all_data_node_48_training["energy"])
plt.legend(['Node 7','Node 15','Node 24','Node 33','Node 48'], loc='upper right')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (joules)')
plt.grid(True)
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(14, 5)
plt.plot(all_data_node_7_training["speed"])
plt.plot(all_data_node_15_training["speed"])
plt.plot(all_data_node_24_training["speed"])
plt.plot(all_data_node_33_training["speed"])
plt.plot(all_data_node_48_training["speed"])
plt.legend(['Node 7','Node 15','Node 24','Node 33','Node 48'], loc='upper right')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)
plt.show()

X_data_node_7_training = all_data_node_7_training[0:-1]
X_data_node_7_training.reset_index(drop=True, inplace=True)

X_data_node_15_training = all_data_node_15_training[0:-1]
X_data_node_15_training.reset_index(drop=True, inplace=True)

X_data_node_24_training = all_data_node_24_training[0:-1]
X_data_node_24_training.reset_index(drop=True, inplace=True)

X_data_node_33_training = all_data_node_33_training[0:-1]
X_data_node_33_training.reset_index(drop=True, inplace=True)

X_data_node_48_training = all_data_node_48_training[0:-1]
X_data_node_48_training.reset_index(drop=True, inplace=True)

X_data_node_7_testing = all_data_node_7_testing[0:-1]
X_data_node_7_testing.reset_index(drop=True, inplace=True)

X_data_node_15_testing = all_data_node_15_testing[0:-1]
X_data_node_15_testing.reset_index(drop=True, inplace=True)

X_data_node_24_testing = all_data_node_24_testing[0:-1]
X_data_node_24_testing.reset_index(drop=True, inplace=True)

X_data_node_33_testing = all_data_node_33_testing[0:-1]
X_data_node_33_testing.reset_index(drop=True, inplace=True)

X_data_node_48_testing = all_data_node_48_testing[0:-1]
X_data_node_48_testing.reset_index(drop=True, inplace=True)

y_data_node_7_training = all_data_node_7_training[1:]
y_data_node_7_training.reset_index(drop=True, inplace=True)
y_data_node_7_training.columns = ["pos_x_result","pos_y_result","speed_result","energy_result"]

y_data_node_15_training = all_data_node_15_training[1:]
y_data_node_15_training.reset_index(drop=True, inplace=True)
y_data_node_15_training.columns = ["pos_x_result","pos_y_result","speed_result","energy_result"]

y_data_node_24_training = all_data_node_24_training[1:]
y_data_node_24_training.reset_index(drop=True, inplace=True)
y_data_node_24_training.columns = ["pos_x_result","pos_y_result","speed_result","energy_result"]

y_data_node_33_training = all_data_node_33_training[1:]
y_data_node_33_training.reset_index(drop=True, inplace=True)
y_data_node_33_training.columns = ["pos_x_result","pos_y_result","speed_result","energy_result"]

y_data_node_48_training = all_data_node_48_training[1:]
y_data_node_48_training.reset_index(drop=True, inplace=True)
y_data_node_48_training.columns = ["pos_x_result","pos_y_result","speed_result","energy_result"]

y_data_node_7_testing = all_data_node_7_testing[1:]
y_data_node_7_testing.reset_index(drop=True, inplace=True)
y_data_node_7_testing.columns = ["pos_x_result","pos_y_result","speed_result","energy_result"]

y_data_node_15_testing = all_data_node_15_testing[1:]
y_data_node_15_testing.reset_index(drop=True, inplace=True)
y_data_node_15_testing.columns = ["pos_x_result","pos_y_result","speed_result","energy_result"]

y_data_node_24_testing = all_data_node_24_testing[1:]
y_data_node_24_testing.reset_index(drop=True, inplace=True)
y_data_node_24_testing.columns = ["pos_x_result","pos_y_result","speed_result","energy_result"]

y_data_node_33_testing = all_data_node_33_testing[1:]
y_data_node_33_testing.reset_index(drop=True, inplace=True)
y_data_node_33_testing.columns = ["pos_x_result","pos_y_result","speed_result","energy_result"]

y_data_node_48_testing = all_data_node_48_testing[1:]
y_data_node_48_testing.reset_index(drop=True, inplace=True)
y_data_node_48_testing.columns = ["pos_x_result","pos_y_result","speed_result","energy_result"]

Split Dataset

X_training_data_node_7 = X_data_node_7_training
X_testing_data_node_7 = X_data_node_7_testing

X_training_data_node_15 = X_data_node_15_training
X_testing_data_node_15 = X_data_node_15_testing

X_training_data_node_24 = X_data_node_24_training
X_testing_data_node_24 = X_data_node_24_testing

X_training_data_node_33 = X_data_node_33_training
X_testing_data_node_33 = X_data_node_33_testing

X_training_data_node_48 = X_data_node_48_training
X_testing_data_node_48 = X_data_node_48_testing

y_training_data_node_7 = y_data_node_7_training
y_testing_data_node_7 = y_data_node_7_testing

y_training_data_node_15 = y_data_node_15_training
y_testing_data_node_15 = y_data_node_15_testing

y_training_data_node_24 = y_data_node_24_training
y_testing_data_node_24 = y_data_node_24_testing

y_training_data_node_33 = y_data_node_33_training
y_testing_data_node_33 = y_data_node_33_testing

y_training_data_node_48 = y_data_node_48_training
y_testing_data_node_48 = y_data_node_48_testing

y_training_data_node_7.reset_index(drop=True, inplace=True)
y_training_data_node_7.reset_index(drop=True, inplace=True)
y_training_data_node_15.reset_index(drop=True, inplace=True)
y_training_data_node_15.reset_index(drop=True, inplace=True)
y_training_data_node_24.reset_index(drop=True, inplace=True)
y_training_data_node_24.reset_index(drop=True, inplace=True)
y_training_data_node_33.reset_index(drop=True, inplace=True)
y_training_data_node_33.reset_index(drop=True, inplace=True)
y_training_data_node_48.reset_index(drop=True, inplace=True)
y_training_data_node_48.reset_index(drop=True, inplace=True)

y_training_data_pos_x_node_7 = y_training_data_node_7["pos_x_result"]
y_training_data_pos_y_node_7 = y_training_data_node_7["pos_y_result"]
y_training_data_speed_node_7 = y_training_data_node_7["speed_result"]
y_training_data_energy_node_7 = y_training_data_node_7["energy_result"]

y_testing_data_pos_x_node_7 = y_testing_data_node_7["pos_x_result"]
y_testing_data_pos_y_node_7 = y_testing_data_node_7["pos_y_result"]
y_testing_data_speed_node_7 = y_testing_data_node_7["speed_result"]
y_testing_data_energy_node_7 = y_testing_data_node_7["energy_result"]

y_training_data_pos_x_node_15 = y_training_data_node_15["pos_x_result"]
y_training_data_pos_y_node_15 = y_training_data_node_15["pos_y_result"]
y_training_data_speed_node_15 = y_training_data_node_15["speed_result"]
y_training_data_energy_node_15 = y_training_data_node_15["energy_result"]

y_testing_data_pos_x_node_15 = y_testing_data_node_15["pos_x_result"]
y_testing_data_pos_y_node_15 = y_testing_data_node_15["pos_y_result"]
y_testing_data_speed_node_15 = y_testing_data_node_15["speed_result"]
y_testing_data_energy_node_15 = y_testing_data_node_15["energy_result"]

y_training_data_pos_x_node_24 = y_training_data_node_24["pos_x_result"]
y_training_data_pos_y_node_24 = y_training_data_node_24["pos_y_result"]
y_training_data_speed_node_24 = y_training_data_node_24["speed_result"]
y_training_data_energy_node_24 = y_training_data_node_24["energy_result"]

y_testing_data_pos_x_node_24 = y_testing_data_node_24["pos_x_result"]
y_testing_data_pos_y_node_24 = y_testing_data_node_24["pos_y_result"]
y_testing_data_speed_node_24 = y_testing_data_node_24["speed_result"]
y_testing_data_energy_node_24 = y_testing_data_node_24["energy_result"]

y_training_data_pos_x_node_33 = y_training_data_node_33["pos_x_result"]
y_training_data_pos_y_node_33 = y_training_data_node_33["pos_y_result"]
y_training_data_speed_node_33 = y_training_data_node_33["speed_result"]
y_training_data_energy_node_33 = y_training_data_node_33["energy_result"]

y_testing_data_pos_x_node_33 = y_testing_data_node_33["pos_x_result"]
y_testing_data_pos_y_node_33 = y_testing_data_node_33["pos_y_result"]
y_testing_data_speed_node_33 = y_testing_data_node_33["speed_result"]
y_testing_data_energy_node_33 = y_testing_data_node_33["energy_result"]

y_training_data_pos_x_node_48 = y_training_data_node_48["pos_x_result"]
y_training_data_pos_y_node_48 = y_training_data_node_48["pos_y_result"]
y_training_data_speed_node_48 = y_training_data_node_48["speed_result"]
y_training_data_energy_node_48 = y_training_data_node_48["energy_result"]

y_testing_data_pos_x_node_48 = y_testing_data_node_48["pos_x_result"]
y_testing_data_pos_y_node_48 = y_testing_data_node_48["pos_y_result"]
y_testing_data_speed_node_48 = y_testing_data_node_48["speed_result"]
y_testing_data_energy_node_48 = y_testing_data_node_48["energy_result"]

y_training_data_pos_x_node_7.reset_index(drop=True, inplace=True)
y_training_data_pos_y_node_7.reset_index(drop=True, inplace=True)
y_training_data_speed_node_7.reset_index(drop=True, inplace=True)
y_training_data_energy_node_7.reset_index(drop=True, inplace=True)
y_testing_data_pos_x_node_7.reset_index(drop=True, inplace=True)
y_testing_data_pos_y_node_7.reset_index(drop=True, inplace=True)
y_testing_data_speed_node_7.reset_index(drop=True, inplace=True)
y_testing_data_energy_node_7.reset_index(drop=True, inplace=True)

y_training_data_pos_x_node_15.reset_index(drop=True, inplace=True)
y_training_data_pos_y_node_15.reset_index(drop=True, inplace=True)
y_training_data_speed_node_15.reset_index(drop=True, inplace=True)
y_training_data_energy_node_15.reset_index(drop=True, inplace=True)
y_testing_data_pos_x_node_15.reset_index(drop=True, inplace=True)
y_testing_data_pos_y_node_15.reset_index(drop=True, inplace=True)
y_testing_data_speed_node_15.reset_index(drop=True, inplace=True)
y_testing_data_energy_node_15.reset_index(drop=True, inplace=True)

y_training_data_pos_x_node_24.reset_index(drop=True, inplace=True)
y_training_data_pos_y_node_24.reset_index(drop=True, inplace=True)
y_training_data_speed_node_24.reset_index(drop=True, inplace=True)
y_training_data_energy_node_24.reset_index(drop=True, inplace=True)
y_testing_data_pos_x_node_24.reset_index(drop=True, inplace=True)
y_testing_data_pos_y_node_24.reset_index(drop=True, inplace=True)
y_testing_data_speed_node_24.reset_index(drop=True, inplace=True)
y_testing_data_energy_node_24.reset_index(drop=True, inplace=True)

y_training_data_pos_x_node_33.reset_index(drop=True, inplace=True)
y_training_data_pos_y_node_33.reset_index(drop=True, inplace=True)
y_training_data_speed_node_33.reset_index(drop=True, inplace=True)
y_training_data_energy_node_33.reset_index(drop=True, inplace=True)
y_testing_data_pos_x_node_33.reset_index(drop=True, inplace=True)
y_testing_data_pos_y_node_33.reset_index(drop=True, inplace=True)
y_testing_data_speed_node_33.reset_index(drop=True, inplace=True)
y_testing_data_energy_node_33.reset_index(drop=True, inplace=True)

y_training_data_pos_x_node_48.reset_index(drop=True, inplace=True)
y_training_data_pos_y_node_48.reset_index(drop=True, inplace=True)
y_training_data_speed_node_48.reset_index(drop=True, inplace=True)
y_training_data_energy_node_48.reset_index(drop=True, inplace=True)
y_testing_data_pos_x_node_48.reset_index(drop=True, inplace=True)
y_testing_data_pos_y_node_48.reset_index(drop=True, inplace=True)
y_testing_data_speed_node_48.reset_index(drop=True, inplace=True)
y_testing_data_energy_node_48.reset_index(drop=True, inplace=True)

Scale Dataset

scaler=MinMaxScaler(feature_range=(0,1))

X_training_data_scale_node_7=scaler.fit_transform(np.array(X_training_data_node_7))
X_testing_data_scale_node_7=scaler.fit_transform(np.array(X_testing_data_node_7))
X_training_data_reshaped_node_7 = X_training_data_scale_node_7.reshape(X_training_data_scale_node_7.shape[0],X_training_data_scale_node_7.shape[1] , 1)
X_testing_data_reshaped_node_7 = X_testing_data_scale_node_7.reshape(X_testing_data_scale_node_7.shape[0],X_testing_data_scale_node_7.shape[1] , 1)

X_training_data_scale_node_15=scaler.fit_transform(np.array(X_training_data_node_15))
X_testing_data_scale_node_15=scaler.fit_transform(np.array(X_testing_data_node_15))
X_training_data_reshaped_node_15 = X_training_data_scale_node_15.reshape(X_training_data_scale_node_15.shape[0],X_training_data_scale_node_15.shape[1] , 1)
X_testing_data_reshaped_node_15 = X_testing_data_scale_node_15.reshape(X_testing_data_scale_node_15.shape[0],X_testing_data_scale_node_15.shape[1] , 1)

X_training_data_scale_node_24=scaler.fit_transform(np.array(X_training_data_node_24))
X_testing_data_scale_node_24=scaler.fit_transform(np.array(X_testing_data_node_24))
X_training_data_reshaped_node_24 = X_training_data_scale_node_24.reshape(X_training_data_scale_node_24.shape[0],X_training_data_scale_node_24.shape[1] , 1)
X_testing_data_reshaped_node_24 = X_testing_data_scale_node_24.reshape(X_testing_data_scale_node_24.shape[0],X_testing_data_scale_node_24.shape[1] , 1)

X_training_data_scale_node_33=scaler.fit_transform(np.array(X_training_data_node_33))
X_testing_data_scale_node_33=scaler.fit_transform(np.array(X_testing_data_node_33))
X_training_data_reshaped_node_33 = X_training_data_scale_node_33.reshape(X_training_data_scale_node_33.shape[0],X_training_data_scale_node_33.shape[1] , 1)
X_testing_data_reshaped_node_33 = X_testing_data_scale_node_33.reshape(X_testing_data_scale_node_33.shape[0],X_testing_data_scale_node_33.shape[1] , 1)

X_training_data_scale_node_48=scaler.fit_transform(np.array(X_training_data_node_48))
X_testing_data_scale_node_48=scaler.fit_transform(np.array(X_testing_data_node_48))
X_training_data_reshaped_node_48 = X_training_data_scale_node_48.reshape(X_training_data_scale_node_48.shape[0],X_training_data_scale_node_48.shape[1] , 1)
X_testing_data_reshaped_node_48 = X_testing_data_scale_node_48.reshape(X_testing_data_scale_node_48.shape[0],X_testing_data_scale_node_48.shape[1] , 1)

--------------------------------------------------------------------------------

Training 6 Machine Learning Models

--------------------------------------------------------------------------------

============================

Stacked LSTM

============================

Stacked_LSTM_Model_pos_x_node_7 = Sequential()
Stacked_LSTM_Model_pos_x_node_7.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_pos_x_node_7.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_pos_x_node_7.add(LSTM(50))
Stacked_LSTM_Model_pos_x_node_7.add(Dense(1))
Stacked_LSTM_Model_pos_x_node_7.compile(loss='mean_squared_error',optimizer='adam')
Stacked_LSTM_Model_pos_y_node_7=Sequential()
Stacked_LSTM_Model_pos_y_node_7.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_pos_y_node_7.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_pos_y_node_7.add(LSTM(50))
Stacked_LSTM_Model_pos_y_node_7.add(Dense(1))
Stacked_LSTM_Model_pos_y_node_7.compile(loss='mean_squared_error',optimizer='adam')
Stacked_LSTM_Model_speed_node_7=Sequential()
Stacked_LSTM_Model_speed_node_7.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_speed_node_7.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_speed_node_7.add(LSTM(50))
Stacked_LSTM_Model_speed_node_7.add(Dense(1))
Stacked_LSTM_Model_speed_node_7.compile(loss='mean_squared_error',optimizer='adam')
Stacked_LSTM_Model_energy_node_7=Sequential()
Stacked_LSTM_Model_energy_node_7.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_energy_node_7.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_energy_node_7.add(LSTM(50))
Stacked_LSTM_Model_energy_node_7.add(Dense(1))
Stacked_LSTM_Model_energy_node_7.compile(loss='mean_squared_error',optimizer='adam')

Stacked_LSTM_Model_pos_x_node_15 = Sequential()
Stacked_LSTM_Model_pos_x_node_15.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_pos_x_node_15.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_pos_x_node_15.add(LSTM(50))
Stacked_LSTM_Model_pos_x_node_15.add(Dense(1))
Stacked_LSTM_Model_pos_x_node_15.compile(loss='mean_squared_error',optimizer='adam')
Stacked_LSTM_Model_pos_y_node_15=Sequential()
Stacked_LSTM_Model_pos_y_node_15.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_pos_y_node_15.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_pos_y_node_15.add(LSTM(50))
Stacked_LSTM_Model_pos_y_node_15.add(Dense(1))
Stacked_LSTM_Model_pos_y_node_15.compile(loss='mean_squared_error',optimizer='adam')
Stacked_LSTM_Model_speed_node_15=Sequential()
Stacked_LSTM_Model_speed_node_15.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_speed_node_15.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_speed_node_15.add(LSTM(50))
Stacked_LSTM_Model_speed_node_15.add(Dense(1))
Stacked_LSTM_Model_speed_node_15.compile(loss='mean_squared_error',optimizer='adam')
Stacked_LSTM_Model_energy_node_15=Sequential()
Stacked_LSTM_Model_energy_node_15.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_energy_node_15.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_energy_node_15.add(LSTM(50))
Stacked_LSTM_Model_energy_node_15.add(Dense(1))
Stacked_LSTM_Model_energy_node_15.compile(loss='mean_squared_error',optimizer='adam')

Stacked_LSTM_Model_pos_x_node_24 = Sequential()
Stacked_LSTM_Model_pos_x_node_24.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_pos_x_node_24.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_pos_x_node_24.add(LSTM(50))
Stacked_LSTM_Model_pos_x_node_24.add(Dense(1))
Stacked_LSTM_Model_pos_x_node_24.compile(loss='mean_squared_error',optimizer='adam')
Stacked_LSTM_Model_pos_y_node_24=Sequential()
Stacked_LSTM_Model_pos_y_node_24.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_pos_y_node_24.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_pos_y_node_24.add(LSTM(50))
Stacked_LSTM_Model_pos_y_node_24.add(Dense(1))
Stacked_LSTM_Model_pos_y_node_24.compile(loss='mean_squared_error',optimizer='adam')
Stacked_LSTM_Model_speed_node_24=Sequential()
Stacked_LSTM_Model_speed_node_24.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_speed_node_24.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_speed_node_24.add(LSTM(50))
Stacked_LSTM_Model_speed_node_24.add(Dense(1))
Stacked_LSTM_Model_speed_node_24.compile(loss='mean_squared_error',optimizer='adam')
Stacked_LSTM_Model_energy_node_24=Sequential()
Stacked_LSTM_Model_energy_node_24.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_energy_node_24.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_energy_node_24.add(LSTM(50))
Stacked_LSTM_Model_energy_node_24.add(Dense(1))
Stacked_LSTM_Model_energy_node_24.compile(loss='mean_squared_error',optimizer='adam')

Stacked_LSTM_Model_pos_x_node_33 = Sequential()
Stacked_LSTM_Model_pos_x_node_33.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_pos_x_node_33.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_pos_x_node_33.add(LSTM(50))
Stacked_LSTM_Model_pos_x_node_33.add(Dense(1))
Stacked_LSTM_Model_pos_x_node_33.compile(loss='mean_squared_error',optimizer='adam')
Stacked_LSTM_Model_pos_y_node_33=Sequential()
Stacked_LSTM_Model_pos_y_node_33.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_pos_y_node_33.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_pos_y_node_33.add(LSTM(50))
Stacked_LSTM_Model_pos_y_node_33.add(Dense(1))
Stacked_LSTM_Model_pos_y_node_33.compile(loss='mean_squared_error',optimizer='adam')
Stacked_LSTM_Model_speed_node_33=Sequential()
Stacked_LSTM_Model_speed_node_33.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_speed_node_33.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_speed_node_33.add(LSTM(50))
Stacked_LSTM_Model_speed_node_33.add(Dense(1))
Stacked_LSTM_Model_speed_node_33.compile(loss='mean_squared_error',optimizer='adam')
Stacked_LSTM_Model_energy_node_33=Sequential()
Stacked_LSTM_Model_energy_node_33.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_energy_node_33.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_energy_node_33.add(LSTM(50))
Stacked_LSTM_Model_energy_node_33.add(Dense(1))
Stacked_LSTM_Model_energy_node_33.compile(loss='mean_squared_error',optimizer='adam')

Stacked_LSTM_Model_pos_x_node_48 = Sequential()
Stacked_LSTM_Model_pos_x_node_48.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_pos_x_node_48.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_pos_x_node_48.add(LSTM(50))
Stacked_LSTM_Model_pos_x_node_48.add(Dense(1))
Stacked_LSTM_Model_pos_x_node_48.compile(loss='mean_squared_error',optimizer='adam')
Stacked_LSTM_Model_pos_y_node_48=Sequential()
Stacked_LSTM_Model_pos_y_node_48.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_pos_y_node_48.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_pos_y_node_48.add(LSTM(50))
Stacked_LSTM_Model_pos_y_node_48.add(Dense(1))
Stacked_LSTM_Model_pos_y_node_48.compile(loss='mean_squared_error',optimizer='adam')
Stacked_LSTM_Model_speed_node_48=Sequential()
Stacked_LSTM_Model_speed_node_48.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_speed_node_48.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_speed_node_48.add(LSTM(50))
Stacked_LSTM_Model_speed_node_48.add(Dense(1))
Stacked_LSTM_Model_speed_node_48.compile(loss='mean_squared_error',optimizer='adam')
Stacked_LSTM_Model_energy_node_48=Sequential()
Stacked_LSTM_Model_energy_node_48.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_energy_node_48.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_energy_node_48.add(LSTM(50))
Stacked_LSTM_Model_energy_node_48.add(Dense(1))
Stacked_LSTM_Model_energy_node_48.compile(loss='mean_squared_error',optimizer='adam')

Stacked_LSTM_Model_pos_x_node_7.fit(X_training_data_reshaped_node_7,y_training_data_pos_x_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_pos_x_node_7),epochs=5,batch_size=10,verbose=1)
Stacked_LSTM_Model_pos_y_node_7.fit(X_training_data_reshaped_node_7,y_training_data_pos_y_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_pos_y_node_7),epochs=5,batch_size=10,verbose=1)
Stacked_LSTM_Model_speed_node_7.fit(X_training_data_reshaped_node_7,y_training_data_speed_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_speed_node_7),epochs=5,batch_size=10,verbose=1)
Stacked_LSTM_Model_energy_node_7.fit(X_training_data_reshaped_node_7,y_training_data_energy_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_energy_node_7),epochs=5,batch_size=10,verbose=1)

Stacked_LSTM_Model_pos_x_node_15.fit(X_training_data_reshaped_node_15,y_training_data_pos_x_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_pos_x_node_15),epochs=5,batch_size=10,verbose=1)
Stacked_LSTM_Model_pos_y_node_15.fit(X_training_data_reshaped_node_15,y_training_data_pos_y_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_pos_y_node_15),epochs=5,batch_size=10,verbose=1)
Stacked_LSTM_Model_speed_node_15.fit(X_training_data_reshaped_node_15,y_training_data_speed_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_speed_node_15),epochs=5,batch_size=10,verbose=1)
Stacked_LSTM_Model_energy_node_15.fit(X_training_data_reshaped_node_15,y_training_data_energy_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_energy_node_15),epochs=5,batch_size=10,verbose=1)

Stacked_LSTM_Model_pos_x_node_24.fit(X_training_data_reshaped_node_24,y_training_data_pos_x_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_pos_x_node_24),epochs=5,batch_size=10,verbose=1)
Stacked_LSTM_Model_pos_y_node_24.fit(X_training_data_reshaped_node_24,y_training_data_pos_y_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_pos_y_node_24),epochs=5,batch_size=10,verbose=1)
Stacked_LSTM_Model_speed_node_24.fit(X_training_data_reshaped_node_24,y_training_data_speed_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_speed_node_24),epochs=5,batch_size=10,verbose=1)
Stacked_LSTM_Model_energy_node_24.fit(X_training_data_reshaped_node_24,y_training_data_energy_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_energy_node_24),epochs=5,batch_size=10,verbose=1)

Stacked_LSTM_Model_pos_x_node_33.fit(X_training_data_reshaped_node_33,y_training_data_pos_x_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_pos_x_node_33),epochs=5,batch_size=10,verbose=1)
Stacked_LSTM_Model_pos_y_node_33.fit(X_training_data_reshaped_node_33,y_training_data_pos_y_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_pos_y_node_33),epochs=5,batch_size=10,verbose=1)
Stacked_LSTM_Model_speed_node_33.fit(X_training_data_reshaped_node_33,y_training_data_speed_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_speed_node_33),epochs=5,batch_size=10,verbose=1)
Stacked_LSTM_Model_energy_node_33.fit(X_training_data_reshaped_node_33,y_training_data_energy_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_energy_node_33),epochs=5,batch_size=10,verbose=1)

Stacked_LSTM_Model_pos_x_node_48.fit(X_training_data_reshaped_node_48,y_training_data_pos_x_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_pos_x_node_48),epochs=5,batch_size=10,verbose=1)
Stacked_LSTM_Model_pos_y_node_48.fit(X_training_data_reshaped_node_48,y_training_data_pos_y_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_pos_y_node_48),epochs=5,batch_size=10,verbose=1)
Stacked_LSTM_Model_speed_node_48.fit(X_training_data_reshaped_node_48,y_training_data_speed_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_speed_node_48),epochs=5,batch_size=10,verbose=1)
Stacked_LSTM_Model_energy_node_48.fit(X_training_data_reshaped_node_48,y_training_data_energy_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_energy_node_48),epochs=5,batch_size=10,verbose=1)

Epoch 1/5
195/195 [==============================] - 10s 16ms/step - loss: 35404.8434 - val_loss: 24487.6895
Epoch 2/5
195/195 [==============================] - 2s 8ms/step - loss: 30331.0568 - val_loss: 21753.3633
Epoch 3/5
195/195 [==============================] - 2s 8ms/step - loss: 27185.3495 - val_loss: 19361.6699
Epoch 4/5
195/195 [==============================] - 2s 8ms/step - loss: 24208.6902 - val_loss: 17247.7539
Epoch 5/5
195/195 [==============================] - 2s 8ms/step - loss: 21791.9678 - val_loss: 15371.4697
Epoch 1/5
195/195 [==============================] - 11s 20ms/step - loss: 43494.2660 - val_loss: 22608.0996
Epoch 2/5
195/195 [==============================] - 2s 8ms/step - loss: 38799.0316 - val_loss: 19769.2383
Epoch 3/5
195/195 [==============================] - 2s 8ms/step - loss: 35476.2642 - val_loss: 17293.7500
Epoch 4/5
195/195 [==============================] - 2s 8ms/step - loss: 33001.7900 - val_loss: 15087.7979
Epoch 5/5
195/195 [==============================] - 2s 8ms/step - loss: 28298.0404 - val_loss: 13120.0029
Epoch 1/5
195/195 [==============================] - 10s 17ms/step - loss: 9.5433 - val_loss: 10.0850
Epoch 2/5
195/195 [==============================] - 1s 7ms/step - loss: 3.6667 - val_loss: 2.8820
Epoch 3/5
195/195 [==============================] - 1s 7ms/step - loss: 1.4926 - val_loss: 2.4370
Epoch 4/5
195/195 [==============================] - 1s 7ms/step - loss: 1.2004 - val_loss: 1.5779
Epoch 5/5
195/195 [==============================] - 1s 7ms/step - loss: 1.1032 - val_loss: 1.7487
Epoch 1/5
195/195 [==============================] - 10s 16ms/step - loss: 278343.0282 - val_loss: 1309.2938
Epoch 2/5
195/195 [==============================] - 1s 7ms/step - loss: 283466.8535 - val_loss: 1614.3088
Epoch 3/5
195/195 [==============================] - 1s 7ms/step - loss: 276567.1197 - val_loss: 2096.7578
Epoch 4/5
195/195 [==============================] - 1s 7ms/step - loss: 236797.0820 - val_loss: 2746.3916
Epoch 5/5
195/195 [==============================] - 1s 7ms/step - loss: 248735.6896 - val_loss: 3558.8145
Epoch 1/5
195/195 [==============================] - 10s 15ms/step - loss: 57826.9343 - val_loss: 33340.3359
Epoch 2/5
195/195 [==============================] - 1s 7ms/step - loss: 52662.6127 - val_loss: 29837.8594
Epoch 3/5
195/195 [==============================] - 1s 7ms/step - loss: 45728.3085 - val_loss: 26717.7422
Epoch 4/5
195/195 [==============================] - 1s 7ms/step - loss: 43885.9411 - val_loss: 23889.7852
Epoch 5/5
195/195 [==============================] - 1s 7ms/step - loss: 40847.6358 - val_loss: 21308.4844
Epoch 1/5
195/195 [==============================] - 10s 15ms/step - loss: 64234.4358 - val_loss: 46540.3008
Epoch 2/5
195/195 [==============================] - 1s 7ms/step - loss: 55935.6164 - val_loss: 42188.8477
Epoch 3/5
195/195 [==============================] - 2s 8ms/step - loss: 49868.2291 - val_loss: 38262.3906
Epoch 4/5
195/195 [==============================] - 2s 8ms/step - loss: 47097.2517 - val_loss: 34644.8281
Epoch 5/5
195/195 [==============================] - 1s 8ms/step - loss: 43139.5754 - val_loss: 31304.1465
Epoch 1/5
195/195 [==============================] - 11s 16ms/step - loss: 6.1593 - val_loss: 7.3322
Epoch 2/5
195/195 [==============================] - 1s 7ms/step - loss: 3.8444 - val_loss: 1.1021
Epoch 3/5
195/195 [==============================] - 1s 7ms/step - loss: 0.8383 - val_loss: 1.8419
Epoch 4/5
195/195 [==============================] - 1s 7ms/step - loss: 0.3910 - val_loss: 1.8153
Epoch 5/5
195/195 [==============================] - 1s 7ms/step - loss: 0.3124 - val_loss: 1.7810
Epoch 1/5
195/195 [==============================] - 10s 15ms/step - loss: 504451.3052 - val_loss: 249062.6562
Epoch 2/5
195/195 [==============================] - 1s 8ms/step - loss: 483989.0901 - val_loss: 243638.9375
Epoch 3/5
195/195 [==============================] - 1s 7ms/step - loss: 491921.4145 - val_loss: 238670.5312
Epoch 4/5
195/195 [==============================] - 1s 7ms/step - loss: 477795.0973 - val_loss: 234031.9688
Epoch 5/5
195/195 [==============================] - 1s 7ms/step - loss: 463336.5754 - val_loss: 229535.5781
Epoch 1/5
195/195 [==============================] - 12s 16ms/step - loss: 102846.6686 - val_loss: 86165.9375
Epoch 2/5
195/195 [==============================] - 1s 7ms/step - loss: 92540.3809 - val_loss: 80648.9922
Epoch 3/5
195/195 [==============================] - 1s 7ms/step - loss: 87747.9273 - val_loss: 75605.0938
Epoch 4/5
195/195 [==============================] - 1s 7ms/step - loss: 83042.9512 - val_loss: 70893.4609
Epoch 5/5
195/195 [==============================] - 1s 7ms/step - loss: 76862.1336 - val_loss: 66458.4688
Epoch 1/5
195/195 [==============================] - 9s 15ms/step - loss: 20772.0627 - val_loss: 17846.4570
Epoch 2/5
195/195 [==============================] - 1s 7ms/step - loss: 16939.2615 - val_loss: 15895.0820
Epoch 3/5
195/195 [==============================] - 1s 7ms/step - loss: 15153.4294 - val_loss: 14280.1904
Epoch 4/5
195/195 [==============================] - 1s 7ms/step - loss: 13472.7960 - val_loss: 12918.3984
Epoch 5/5
195/195 [==============================] - 1s 7ms/step - loss: 11911.1548 - val_loss: 11771.5586
Epoch 1/5
195/195 [==============================] - 13s 18ms/step - loss: 5.8036 - val_loss: 5.4938
Epoch 2/5
195/195 [==============================] - 1s 7ms/step - loss: 1.6152 - val_loss: 6.4268
Epoch 3/5
195/195 [==============================] - 1s 7ms/step - loss: 1.1218 - val_loss: 6.4163
Epoch 4/5
195/195 [==============================] - 1s 7ms/step - loss: 0.7970 - val_loss: 5.3241
Epoch 5/5
195/195 [==============================] - 2s 9ms/step - loss: 0.6300 - val_loss: 4.5645
Epoch 1/5
195/195 [==============================] - 12s 19ms/step - loss: 2411086.4420 - val_loss: 1040500.8750
Epoch 2/5
195/195 [==============================] - 2s 8ms/step - loss: 2399515.2870 - val_loss: 1022647.5625
Epoch 3/5
195/195 [==============================] - 1s 8ms/step - loss: 2406287.7666 - val_loss: 1005671.3750
Epoch 4/5
195/195 [==============================] - 1s 8ms/step - loss: 2315998.2653 - val_loss: 989083.8125
Epoch 5/5
195/195 [==============================] - 1s 7ms/step - loss: 2372805.2997 - val_loss: 972943.5000
Epoch 1/5
195/195 [==============================] - 10s 15ms/step - loss: 84658.5351 - val_loss: 52894.5195
Epoch 2/5
195/195 [==============================] - 1s 7ms/step - loss: 75128.8651 - val_loss: 48505.4414
Epoch 3/5
195/195 [==============================] - 1s 7ms/step - loss: 71549.9389 - val_loss: 44559.5859
Epoch 4/5
195/195 [==============================] - 1s 7ms/step - loss: 65028.6919 - val_loss: 40907.2109
Epoch 5/5
195/195 [==============================] - 1s 7ms/step - loss: 58925.0184 - val_loss: 37523.3867
Epoch 1/5
195/195 [==============================] - 13s 16ms/step - loss: 77446.4221 - val_loss: 65674.3125
Epoch 2/5
195/195 [==============================] - 1s 8ms/step - loss: 69102.8956 - val_loss: 60765.0117
Epoch 3/5
195/195 [==============================] - 1s 7ms/step - loss: 63290.4534 - val_loss: 56310.6016
Epoch 4/5
195/195 [==============================] - 1s 7ms/step - loss: 58588.0302 - val_loss: 52161.9141
Epoch 5/5
195/195 [==============================] - 1s 7ms/step - loss: 55231.5423 - val_loss: 48307.6250
Epoch 1/5
195/195 [==============================] - 10s 16ms/step - loss: 6.4093 - val_loss: 2.1220
Epoch 2/5
195/195 [==============================] - 1s 7ms/step - loss: 3.8589 - val_loss: 1.9840
Epoch 3/5
195/195 [==============================] - 1s 7ms/step - loss: 2.3632 - val_loss: 2.9213
Epoch 4/5
195/195 [==============================] - 1s 7ms/step - loss: 1.6746 - val_loss: 1.5012
Epoch 5/5
195/195 [==============================] - 2s 8ms/step - loss: 0.5045 - val_loss: 0.7836
Epoch 1/5
195/195 [==============================] - 9s 14ms/step - loss: 721081.0902 - val_loss: 258727.9688
Epoch 2/5
195/195 [==============================] - 1s 7ms/step - loss: 702575.8607 - val_loss: 250149.6406
Epoch 3/5
195/195 [==============================] - 1s 7ms/step - loss: 686481.9416 - val_loss: 242078.5312
Epoch 4/5
195/195 [==============================] - 2s 8ms/step - loss: 647509.5416 - val_loss: 234364.8125
Epoch 5/5
195/195 [==============================] - 1s 8ms/step - loss: 691256.6129 - val_loss: 226927.8594
Epoch 1/5
195/195 [==============================] - 14s 17ms/step - loss: 150786.7159 - val_loss: 129908.9922
Epoch 2/5
195/195 [==============================] - 2s 8ms/step - loss: 137967.8961 - val_loss: 122434.6094
Epoch 3/5
195/195 [==============================] - 2s 8ms/step - loss: 130355.6572 - val_loss: 115510.3438
Epoch 4/5
195/195 [==============================] - 1s 8ms/step - loss: 122556.7420 - val_loss: 108948.6406
Epoch 5/5
195/195 [==============================] - 1s 7ms/step - loss: 116525.1445 - val_loss: 102700.1328
Epoch 1/5
195/195 [==============================] - 9s 15ms/step - loss: 21878.5251 - val_loss: 17574.2754
Epoch 2/5
195/195 [==============================] - 1s 7ms/step - loss: 17270.4904 - val_loss: 14963.8164
Epoch 3/5
195/195 [==============================] - 1s 7ms/step - loss: 14753.5499 - val_loss: 12726.0439
Epoch 4/5
195/195 [==============================] - 1s 7ms/step - loss: 12557.7306 - val_loss: 10765.2725
Epoch 5/5
195/195 [==============================] - 2s 8ms/step - loss: 10644.5731 - val_loss: 9044.4443
Epoch 1/5
195/195 [==============================] - 10s 15ms/step - loss: 8.7518 - val_loss: 8.6165
Epoch 2/5
195/195 [==============================] - 1s 7ms/step - loss: 3.9975 - val_loss: 11.4630
Epoch 3/5
195/195 [==============================] - 1s 8ms/step - loss: 3.5645 - val_loss: 13.8317
Epoch 4/5
195/195 [==============================] - 1s 7ms/step - loss: 1.7943 - val_loss: 11.4257
Epoch 5/5
195/195 [==============================] - 1s 7ms/step - loss: 0.8973 - val_loss: 5.7834
Epoch 1/5
195/195 [==============================] - 10s 19ms/step - loss: 4172980.4974 - val_loss: 408993.7812
Epoch 2/5
195/195 [==============================] - 2s 8ms/step - loss: 4150819.7895 - val_loss: 395902.3438
Epoch 3/5
195/195 [==============================] - 1s 8ms/step - loss: 4029003.4974 - val_loss: 383476.9688
Epoch 4/5
195/195 [==============================] - 2s 9ms/step - loss: 4043019.1696 - val_loss: 371417.8438
Epoch 5/5
195/195 [==============================] - 1s 7ms/step - loss: 4022305.3253 - val_loss: 359708.8438

<tensorflow.python.keras.callbacks.History at 0x195045095b0>

train_predict_Stacked_LSTM_Model_pos_x_node_7 = Stacked_LSTM_Model_pos_x_node_7.predict(X_training_data_reshaped_node_7)
test_predict_Stacked_LSTM_Model_pos_x_node_7 = Stacked_LSTM_Model_pos_x_node_7.predict(X_testing_data_reshaped_node_7)
train_predict_Stacked_LSTM_Model_pos_y_node_7 = Stacked_LSTM_Model_pos_y_node_7.predict(X_training_data_reshaped_node_7)
test_predict_Stacked_LSTM_Model_pos_y_node_7 = Stacked_LSTM_Model_pos_y_node_7.predict(X_testing_data_reshaped_node_7)
train_predict_Stacked_LSTM_Model_speed_node_7 = Stacked_LSTM_Model_speed_node_7.predict(X_training_data_reshaped_node_7)
test_predict_Stacked_LSTM_Model_speed_node_7 = Stacked_LSTM_Model_speed_node_7.predict(X_testing_data_reshaped_node_7)
train_predict_Stacked_LSTM_Model_energy_node_7 = Stacked_LSTM_Model_energy_node_7.predict(X_training_data_reshaped_node_7)
test_predict_Stacked_LSTM_Model_energy_node_7 = Stacked_LSTM_Model_energy_node_7.predict(X_testing_data_reshaped_node_7)

train_predict_Stacked_LSTM_Model_pos_x_node_15 = Stacked_LSTM_Model_pos_x_node_15.predict(X_training_data_reshaped_node_15)
test_predict_Stacked_LSTM_Model_pos_x_node_15 = Stacked_LSTM_Model_pos_x_node_15.predict(X_testing_data_reshaped_node_15)
train_predict_Stacked_LSTM_Model_pos_y_node_15 = Stacked_LSTM_Model_pos_y_node_15.predict(X_training_data_reshaped_node_15)
test_predict_Stacked_LSTM_Model_pos_y_node_15 = Stacked_LSTM_Model_pos_y_node_15.predict(X_testing_data_reshaped_node_15)
train_predict_Stacked_LSTM_Model_speed_node_15 = Stacked_LSTM_Model_speed_node_15.predict(X_training_data_reshaped_node_15)
test_predict_Stacked_LSTM_Model_speed_node_15 = Stacked_LSTM_Model_speed_node_15.predict(X_testing_data_reshaped_node_15)
train_predict_Stacked_LSTM_Model_energy_node_15 = Stacked_LSTM_Model_energy_node_15.predict(X_training_data_reshaped_node_15)
test_predict_Stacked_LSTM_Model_energy_node_15 = Stacked_LSTM_Model_energy_node_15.predict(X_testing_data_reshaped_node_15)

train_predict_Stacked_LSTM_Model_pos_x_node_24 = Stacked_LSTM_Model_pos_x_node_24.predict(X_training_data_reshaped_node_24)
test_predict_Stacked_LSTM_Model_pos_x_node_24 = Stacked_LSTM_Model_pos_x_node_24.predict(X_testing_data_reshaped_node_24)
train_predict_Stacked_LSTM_Model_pos_y_node_24 = Stacked_LSTM_Model_pos_y_node_24.predict(X_training_data_reshaped_node_24)
test_predict_Stacked_LSTM_Model_pos_y_node_24 = Stacked_LSTM_Model_pos_y_node_24.predict(X_testing_data_reshaped_node_24)
train_predict_Stacked_LSTM_Model_speed_node_24 = Stacked_LSTM_Model_speed_node_24.predict(X_training_data_reshaped_node_24)
test_predict_Stacked_LSTM_Model_speed_node_24 = Stacked_LSTM_Model_speed_node_24.predict(X_testing_data_reshaped_node_24)
train_predict_Stacked_LSTM_Model_energy_node_24 = Stacked_LSTM_Model_energy_node_24.predict(X_training_data_reshaped_node_24)
test_predict_Stacked_LSTM_Model_energy_node_24 = Stacked_LSTM_Model_energy_node_24.predict(X_testing_data_reshaped_node_24)

train_predict_Stacked_LSTM_Model_pos_x_node_33 = Stacked_LSTM_Model_pos_x_node_33.predict(X_training_data_reshaped_node_33)
test_predict_Stacked_LSTM_Model_pos_x_node_33 = Stacked_LSTM_Model_pos_x_node_33.predict(X_testing_data_reshaped_node_33)
train_predict_Stacked_LSTM_Model_pos_y_node_33 = Stacked_LSTM_Model_pos_y_node_33.predict(X_training_data_reshaped_node_33)
test_predict_Stacked_LSTM_Model_pos_y_node_33 = Stacked_LSTM_Model_pos_y_node_33.predict(X_testing_data_reshaped_node_33)
train_predict_Stacked_LSTM_Model_speed_node_33 = Stacked_LSTM_Model_speed_node_33.predict(X_training_data_reshaped_node_33)
test_predict_Stacked_LSTM_Model_speed_node_33 = Stacked_LSTM_Model_speed_node_33.predict(X_testing_data_reshaped_node_33)
train_predict_Stacked_LSTM_Model_energy_node_33 = Stacked_LSTM_Model_energy_node_33.predict(X_training_data_reshaped_node_33)
test_predict_Stacked_LSTM_Model_energy_node_33 = Stacked_LSTM_Model_energy_node_33.predict(X_testing_data_reshaped_node_33)

train_predict_Stacked_LSTM_Model_pos_x_node_48 = Stacked_LSTM_Model_pos_x_node_48.predict(X_training_data_reshaped_node_48)
test_predict_Stacked_LSTM_Model_pos_x_node_48 = Stacked_LSTM_Model_pos_x_node_48.predict(X_testing_data_reshaped_node_48)
train_predict_Stacked_LSTM_Model_pos_y_node_48 = Stacked_LSTM_Model_pos_y_node_48.predict(X_training_data_reshaped_node_48)
test_predict_Stacked_LSTM_Model_pos_y_node_48 = Stacked_LSTM_Model_pos_y_node_48.predict(X_testing_data_reshaped_node_48)
train_predict_Stacked_LSTM_Model_speed_node_48 = Stacked_LSTM_Model_speed_node_48.predict(X_training_data_reshaped_node_48)
test_predict_Stacked_LSTM_Model_speed_node_48 = Stacked_LSTM_Model_speed_node_48.predict(X_testing_data_reshaped_node_48)
train_predict_Stacked_LSTM_Model_energy_node_48 = Stacked_LSTM_Model_energy_node_48.predict(X_training_data_reshaped_node_48)
test_predict_Stacked_LSTM_Model_energy_node_48 = Stacked_LSTM_Model_energy_node_48.predict(X_testing_data_reshaped_node_48)

RMSE

print("\n\nRMSE on Training Data by Stacked LSTM: ")
print("======================================\n\n")

print("\n\nRMSE of Node 7: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_7,train_predict_Stacked_LSTM_Model_pos_x_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_7,train_predict_Stacked_LSTM_Model_pos_y_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_7,train_predict_Stacked_LSTM_Model_speed_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_7,train_predict_Stacked_LSTM_Model_energy_node_7)))
      
print("\n\nRMSE of Node 15: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_15,train_predict_Stacked_LSTM_Model_pos_x_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_15,train_predict_Stacked_LSTM_Model_pos_y_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_15,train_predict_Stacked_LSTM_Model_speed_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_15,train_predict_Stacked_LSTM_Model_energy_node_15)))
      
print("\n\nRMSE of Node 24: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_24,train_predict_Stacked_LSTM_Model_pos_x_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_24,train_predict_Stacked_LSTM_Model_pos_y_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_24,train_predict_Stacked_LSTM_Model_speed_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_24,train_predict_Stacked_LSTM_Model_energy_node_24)))

print("\n\nRMSE of Node 33: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_33,train_predict_Stacked_LSTM_Model_pos_x_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_33,train_predict_Stacked_LSTM_Model_pos_y_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_33,train_predict_Stacked_LSTM_Model_speed_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_33,train_predict_Stacked_LSTM_Model_energy_node_33)))
      
print("\n\nRMSE of Node 48: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_48,train_predict_Stacked_LSTM_Model_pos_x_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_48,train_predict_Stacked_LSTM_Model_pos_y_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_48,train_predict_Stacked_LSTM_Model_speed_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_48,train_predict_Stacked_LSTM_Model_energy_node_48)))

print("\n\nRMSE on Testing Data by Stacked LSTM: ")
print("=====================================\n\n")
      
print("\n\nRMSE of Node 7: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_Stacked_LSTM_Model_pos_x_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_Stacked_LSTM_Model_pos_y_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_Stacked_LSTM_Model_speed_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_Stacked_LSTM_Model_energy_node_7)))
      
print("\n\nRMSE of Node 15: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_Stacked_LSTM_Model_pos_x_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_Stacked_LSTM_Model_pos_y_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_Stacked_LSTM_Model_speed_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_Stacked_LSTM_Model_energy_node_15)))
     
print("\n\nRMSE of Node 24: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_Stacked_LSTM_Model_pos_x_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_24,test_predict_Stacked_LSTM_Model_pos_y_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_Stacked_LSTM_Model_speed_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_Stacked_LSTM_Model_energy_node_24)))
      
print("\n\nRMSE of Node 33: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_Stacked_LSTM_Model_pos_x_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_Stacked_LSTM_Model_pos_y_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_Stacked_LSTM_Model_speed_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_Stacked_LSTM_Model_energy_node_33)))
      
print("\n\nRMSE of Node 48: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_Stacked_LSTM_Model_pos_x_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_Stacked_LSTM_Model_pos_y_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_Stacked_LSTM_Model_speed_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_Stacked_LSTM_Model_energy_node_48)))

RMSE on Training Data by Stacked LSTM: 
======================================




RMSE of Node 7: 
======================================


142.4267948552979
166.37859153995095
1.0202161460596793
494.8003287845379


RMSE of Node 15: 
======================================


194.7692518118867
202.2210001026537
0.5617987351372188
676.4490717338922


RMSE of Node 24: 
======================================


271.1026511675998
106.22371390968759
0.7309696527713134
1513.8217182009498


RMSE of Node 33: 
======================================


239.8506122591158
227.41467845271964
0.53869914764127
811.3053821221465


RMSE of Node 48: 
======================================


333.70620518963227
96.6689433974718
0.6024675893209775
1994.11589192643


RMSE on Testing Data by Stacked LSTM: 
=====================================




RMSE of Node 7: 
======================================


123.981724337066
114.54259473021803
1.3223860744926395
59.6557895808515


RMSE of Node 15: 
======================================


145.97427322191535
176.9297653444743
1.3345308098315403
479.0988241247522


RMSE of Node 24: 
======================================


257.7954130575904
108.49681331079339
2.1364596212758826
986.3790117496548


RMSE of Node 33: 
======================================


193.70953735607617
219.78996954108516
0.8852174836354741
476.3694606406331


RMSE of Node 48: 
======================================


320.46859908029677
95.10228507476472
2.4048618401773973
599.7573180351176

Graph

print("\n\nGraph of Node 7: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_7)
plt.plot(test_predict_Stacked_LSTM_Model_pos_x_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_7)
plt.plot(test_predict_Stacked_LSTM_Model_pos_y_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_7)
plt.plot(test_predict_Stacked_LSTM_Model_speed_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_7)
plt.plot(test_predict_Stacked_LSTM_Model_energy_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 15: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_15)
plt.plot(test_predict_Stacked_LSTM_Model_pos_x_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_15)
plt.plot(test_predict_Stacked_LSTM_Model_pos_y_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_15)
plt.plot(test_predict_Stacked_LSTM_Model_speed_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_15)
plt.plot(test_predict_Stacked_LSTM_Model_energy_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 24: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_24)
plt.plot(test_predict_Stacked_LSTM_Model_pos_x_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_24)
plt.plot(test_predict_Stacked_LSTM_Model_pos_y_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_24)
plt.plot(test_predict_Stacked_LSTM_Model_speed_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_24)
plt.plot(test_predict_Stacked_LSTM_Model_energy_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 33: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_33)
plt.plot(test_predict_Stacked_LSTM_Model_pos_x_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_33)
plt.plot(test_predict_Stacked_LSTM_Model_pos_y_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_33)
plt.plot(test_predict_Stacked_LSTM_Model_speed_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_33)
plt.plot(test_predict_Stacked_LSTM_Model_energy_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 48: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_48)
plt.plot(test_predict_Stacked_LSTM_Model_pos_x_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_48)
plt.plot(test_predict_Stacked_LSTM_Model_pos_y_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_48)
plt.plot(test_predict_Stacked_LSTM_Model_speed_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_48)
plt.plot(test_predict_Stacked_LSTM_Model_energy_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

Graph of Node 7: 
======================================

Graph of Node 15: 
======================================

Graph of Node 24: 
======================================

Graph of Node 33: 
======================================

Graph of Node 48: 
======================================

============================

CNN LSTM

============================

X_training_data_reshaped_cnn_node_7 = X_training_data_scale_node_7.reshape(X_training_data_scale_node_7.shape[0],1,X_training_data_scale_node_7.shape[1] , 1)
X_testing_data_reshaped_cnn_node_7 = X_testing_data_scale_node_7.reshape(X_testing_data_scale_node_7.shape[0],1,X_testing_data_scale_node_7.shape[1] , 1)

X_training_data_reshaped_cnn_node_15 = X_training_data_scale_node_15.reshape(X_training_data_scale_node_15.shape[0],1,X_training_data_scale_node_15.shape[1] , 1)
X_testing_data_reshaped_cnn_node_15 = X_testing_data_scale_node_15.reshape(X_testing_data_scale_node_15.shape[0],1,X_testing_data_scale_node_15.shape[1] , 1)

X_training_data_reshaped_cnn_node_24 = X_training_data_scale_node_24.reshape(X_training_data_scale_node_24.shape[0],1,X_training_data_scale_node_24.shape[1] , 1)
X_testing_data_reshaped_cnn_node_24 = X_testing_data_scale_node_24.reshape(X_testing_data_scale_node_24.shape[0],1,X_testing_data_scale_node_24.shape[1] , 1)

X_training_data_reshaped_cnn_node_33 = X_training_data_scale_node_33.reshape(X_training_data_scale_node_33.shape[0],1,X_training_data_scale_node_33.shape[1] , 1)
X_testing_data_reshaped_cnn_node_33 = X_testing_data_scale_node_33.reshape(X_testing_data_scale_node_33.shape[0],1,X_testing_data_scale_node_33.shape[1] , 1)

X_training_data_reshaped_cnn_node_48 = X_training_data_scale_node_48.reshape(X_training_data_scale_node_48.shape[0],1,X_training_data_scale_node_48.shape[1] , 1)
X_testing_data_reshaped_cnn_node_48 = X_testing_data_scale_node_48.reshape(X_testing_data_scale_node_48.shape[0],1,X_testing_data_scale_node_48.shape[1] , 1)

CNN_LSTM_Model_pos_x_node_7 = Sequential()
CNN_LSTM_Model_pos_x_node_7.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_pos_x_node_7.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_pos_x_node_7.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_pos_x_node_7.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_pos_x_node_7.add(Dense(1))
CNN_LSTM_Model_pos_x_node_7.compile(loss='mean_squared_error',optimizer='adam')
CNN_LSTM_Model_pos_y_node_7 = Sequential()
CNN_LSTM_Model_pos_y_node_7.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_pos_y_node_7.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_pos_y_node_7.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_pos_y_node_7.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_pos_y_node_7.add(Dense(1))
CNN_LSTM_Model_pos_y_node_7.compile(loss='mean_squared_error',optimizer='adam')
CNN_LSTM_Model_speed_node_7 = Sequential()
CNN_LSTM_Model_speed_node_7.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_speed_node_7.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_speed_node_7.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_speed_node_7.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_speed_node_7.add(Dense(1))
CNN_LSTM_Model_speed_node_7.compile(loss='mean_squared_error',optimizer='adam')
CNN_LSTM_Model_energy_node_7 = Sequential()
CNN_LSTM_Model_energy_node_7.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_energy_node_7.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_energy_node_7.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_energy_node_7.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_energy_node_7.add(Dense(1))
CNN_LSTM_Model_energy_node_7.compile(loss='mean_squared_error',optimizer='adam')

CNN_LSTM_Model_pos_x_node_15 = Sequential()
CNN_LSTM_Model_pos_x_node_15.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_pos_x_node_15.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_pos_x_node_15.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_pos_x_node_15.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_pos_x_node_15.add(Dense(1))
CNN_LSTM_Model_pos_x_node_15.compile(loss='mean_squared_error',optimizer='adam')
CNN_LSTM_Model_pos_y_node_15 = Sequential()
CNN_LSTM_Model_pos_y_node_15.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_pos_y_node_15.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_pos_y_node_15.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_pos_y_node_15.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_pos_y_node_15.add(Dense(1))
CNN_LSTM_Model_pos_y_node_15.compile(loss='mean_squared_error',optimizer='adam')
CNN_LSTM_Model_speed_node_15 = Sequential()
CNN_LSTM_Model_speed_node_15.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_speed_node_15.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_speed_node_15.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_speed_node_15.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_speed_node_15.add(Dense(1))
CNN_LSTM_Model_speed_node_15.compile(loss='mean_squared_error',optimizer='adam')
CNN_LSTM_Model_energy_node_15 = Sequential()
CNN_LSTM_Model_energy_node_15.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_energy_node_15.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_energy_node_15.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_energy_node_15.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_energy_node_15.add(Dense(1))
CNN_LSTM_Model_energy_node_15.compile(loss='mean_squared_error',optimizer='adam')

CNN_LSTM_Model_pos_x_node_24 = Sequential()
CNN_LSTM_Model_pos_x_node_24.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_pos_x_node_24.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_pos_x_node_24.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_pos_x_node_24.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_pos_x_node_24.add(Dense(1))
CNN_LSTM_Model_pos_x_node_24.compile(loss='mean_squared_error',optimizer='adam')
CNN_LSTM_Model_pos_y_node_24 = Sequential()
CNN_LSTM_Model_pos_y_node_24.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_pos_y_node_24.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_pos_y_node_24.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_pos_y_node_24.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_pos_y_node_24.add(Dense(1))
CNN_LSTM_Model_pos_y_node_24.compile(loss='mean_squared_error',optimizer='adam')
CNN_LSTM_Model_speed_node_24 = Sequential()
CNN_LSTM_Model_speed_node_24.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_speed_node_24.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_speed_node_24.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_speed_node_24.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_speed_node_24.add(Dense(1))
CNN_LSTM_Model_speed_node_24.compile(loss='mean_squared_error',optimizer='adam')
CNN_LSTM_Model_energy_node_24 = Sequential()
CNN_LSTM_Model_energy_node_24.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_energy_node_24.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_energy_node_24.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_energy_node_24.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_energy_node_24.add(Dense(1))
CNN_LSTM_Model_energy_node_24.compile(loss='mean_squared_error',optimizer='adam')

CNN_LSTM_Model_pos_x_node_33 = Sequential()
CNN_LSTM_Model_pos_x_node_33.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_pos_x_node_33.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_pos_x_node_33.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_pos_x_node_33.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_pos_x_node_33.add(Dense(1))
CNN_LSTM_Model_pos_x_node_33.compile(loss='mean_squared_error',optimizer='adam')
CNN_LSTM_Model_pos_y_node_33 = Sequential()
CNN_LSTM_Model_pos_y_node_33.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_pos_y_node_33.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_pos_y_node_33.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_pos_y_node_33.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_pos_y_node_33.add(Dense(1))
CNN_LSTM_Model_pos_y_node_33.compile(loss='mean_squared_error',optimizer='adam')
CNN_LSTM_Model_speed_node_33 = Sequential()
CNN_LSTM_Model_speed_node_33.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_speed_node_33.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_speed_node_33.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_speed_node_33.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_speed_node_33.add(Dense(1))
CNN_LSTM_Model_speed_node_33.compile(loss='mean_squared_error',optimizer='adam')
CNN_LSTM_Model_energy_node_33 = Sequential()
CNN_LSTM_Model_energy_node_33.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_energy_node_33.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_energy_node_33.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_energy_node_33.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_energy_node_33.add(Dense(1))
CNN_LSTM_Model_energy_node_33.compile(loss='mean_squared_error',optimizer='adam')

CNN_LSTM_Model_pos_x_node_48 = Sequential()
CNN_LSTM_Model_pos_x_node_48.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_pos_x_node_48.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_pos_x_node_48.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_pos_x_node_48.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_pos_x_node_48.add(Dense(1))
CNN_LSTM_Model_pos_x_node_48.compile(loss='mean_squared_error',optimizer='adam')
CNN_LSTM_Model_pos_y_node_48 = Sequential()
CNN_LSTM_Model_pos_y_node_48.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_pos_y_node_48.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_pos_y_node_48.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_pos_y_node_48.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_pos_y_node_48.add(Dense(1))
CNN_LSTM_Model_pos_y_node_48.compile(loss='mean_squared_error',optimizer='adam')
CNN_LSTM_Model_speed_node_48 = Sequential()
CNN_LSTM_Model_speed_node_48.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_speed_node_48.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_speed_node_48.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_speed_node_48.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_speed_node_48.add(Dense(1))
CNN_LSTM_Model_speed_node_48.compile(loss='mean_squared_error',optimizer='adam')
CNN_LSTM_Model_energy_node_48 = Sequential()
CNN_LSTM_Model_energy_node_48.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_energy_node_48.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_energy_node_48.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_energy_node_48.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_energy_node_48.add(Dense(1))
CNN_LSTM_Model_energy_node_48.compile(loss='mean_squared_error',optimizer='adam')

CNN_LSTM_Model_pos_x_node_7.fit(X_training_data_reshaped_cnn_node_7,y_training_data_pos_x_node_7,validation_data=(X_testing_data_reshaped_cnn_node_7,y_testing_data_pos_x_node_7),epochs=5,batch_size=10,verbose=1)
CNN_LSTM_Model_pos_y_node_7.fit(X_training_data_reshaped_cnn_node_7,y_training_data_pos_y_node_7,validation_data=(X_testing_data_reshaped_cnn_node_7,y_testing_data_pos_y_node_7),epochs=5,batch_size=10,verbose=1)
CNN_LSTM_Model_speed_node_7.fit(X_training_data_reshaped_cnn_node_7,y_training_data_speed_node_7,validation_data=(X_testing_data_reshaped_cnn_node_7,y_testing_data_speed_node_7),epochs=5,batch_size=10,verbose=1)
CNN_LSTM_Model_energy_node_7.fit(X_training_data_reshaped_cnn_node_7,y_training_data_energy_node_7,validation_data=(X_testing_data_reshaped_cnn_node_7,y_testing_data_energy_node_7),epochs=5,batch_size=10,verbose=1)

CNN_LSTM_Model_pos_x_node_15.fit(X_training_data_reshaped_cnn_node_15,y_training_data_pos_x_node_15,validation_data=(X_testing_data_reshaped_cnn_node_15,y_testing_data_pos_x_node_15),epochs=5,batch_size=10,verbose=1)
CNN_LSTM_Model_pos_y_node_15.fit(X_training_data_reshaped_cnn_node_15,y_training_data_pos_y_node_15,validation_data=(X_testing_data_reshaped_cnn_node_15,y_testing_data_pos_y_node_15),epochs=5,batch_size=10,verbose=1)
CNN_LSTM_Model_speed_node_15.fit(X_training_data_reshaped_cnn_node_15,y_training_data_speed_node_15,validation_data=(X_testing_data_reshaped_cnn_node_15,y_testing_data_speed_node_15),epochs=5,batch_size=10,verbose=1)
CNN_LSTM_Model_energy_node_15.fit(X_training_data_reshaped_cnn_node_15,y_training_data_energy_node_15,validation_data=(X_testing_data_reshaped_cnn_node_15,y_testing_data_energy_node_15),epochs=5,batch_size=10,verbose=1)

CNN_LSTM_Model_pos_x_node_24.fit(X_training_data_reshaped_cnn_node_24,y_training_data_pos_x_node_24,validation_data=(X_testing_data_reshaped_cnn_node_24,y_testing_data_pos_x_node_24),epochs=5,batch_size=10,verbose=1)
CNN_LSTM_Model_pos_y_node_24.fit(X_training_data_reshaped_cnn_node_24,y_training_data_pos_y_node_24,validation_data=(X_testing_data_reshaped_cnn_node_24,y_testing_data_pos_y_node_24),epochs=5,batch_size=10,verbose=1)
CNN_LSTM_Model_speed_node_24.fit(X_training_data_reshaped_cnn_node_24,y_training_data_speed_node_24,validation_data=(X_testing_data_reshaped_cnn_node_24,y_testing_data_speed_node_24),epochs=5,batch_size=10,verbose=1)
CNN_LSTM_Model_energy_node_24.fit(X_training_data_reshaped_cnn_node_24,y_training_data_energy_node_24,validation_data=(X_testing_data_reshaped_cnn_node_24,y_testing_data_energy_node_24),epochs=5,batch_size=10,verbose=1)

CNN_LSTM_Model_pos_x_node_33.fit(X_training_data_reshaped_cnn_node_33,y_training_data_pos_x_node_33,validation_data=(X_testing_data_reshaped_cnn_node_33,y_testing_data_pos_x_node_33),epochs=5,batch_size=10,verbose=1)
CNN_LSTM_Model_pos_y_node_33.fit(X_training_data_reshaped_cnn_node_33,y_training_data_pos_y_node_33,validation_data=(X_testing_data_reshaped_cnn_node_33,y_testing_data_pos_y_node_33),epochs=5,batch_size=10,verbose=1)
CNN_LSTM_Model_speed_node_33.fit(X_training_data_reshaped_cnn_node_33,y_training_data_speed_node_33,validation_data=(X_testing_data_reshaped_cnn_node_33,y_testing_data_speed_node_33),epochs=5,batch_size=10,verbose=1)
CNN_LSTM_Model_energy_node_33.fit(X_training_data_reshaped_cnn_node_33,y_training_data_energy_node_33,validation_data=(X_testing_data_reshaped_cnn_node_33,y_testing_data_energy_node_33),epochs=5,batch_size=10,verbose=1)

CNN_LSTM_Model_pos_x_node_48.fit(X_training_data_reshaped_cnn_node_48,y_training_data_pos_x_node_48,validation_data=(X_testing_data_reshaped_cnn_node_48,y_testing_data_pos_x_node_48),epochs=5,batch_size=10,verbose=1)
CNN_LSTM_Model_pos_y_node_48.fit(X_training_data_reshaped_cnn_node_48,y_training_data_pos_y_node_48,validation_data=(X_testing_data_reshaped_cnn_node_48,y_testing_data_pos_y_node_48),epochs=5,batch_size=10,verbose=1)
CNN_LSTM_Model_speed_node_48.fit(X_training_data_reshaped_cnn_node_48,y_training_data_speed_node_48,validation_data=(X_testing_data_reshaped_cnn_node_48,y_testing_data_speed_node_48),epochs=5,batch_size=10,verbose=1)
CNN_LSTM_Model_energy_node_48.fit(X_training_data_reshaped_cnn_node_48,y_training_data_energy_node_48,validation_data=(X_testing_data_reshaped_cnn_node_48,y_testing_data_energy_node_48),epochs=5,batch_size=10,verbose=1)

Epoch 1/5
195/195 [==============================] - 3s 4ms/step - loss: 36575.6923 - val_loss: 15598.2695
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 10712.0269 - val_loss: 3452.7930
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 3669.6389 - val_loss: 2837.0581
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 3191.9579 - val_loss: 2249.0068
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 2481.8564 - val_loss: 1716.0476
Epoch 1/5
195/195 [==============================] - 3s 4ms/step - loss: 43568.4145 - val_loss: 13012.7236
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 15493.4124 - val_loss: 2764.1025
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 7682.2213 - val_loss: 2805.1321
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 7314.3166 - val_loss: 2854.9714
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 7373.7084 - val_loss: 2907.3884
Epoch 1/5
195/195 [==============================] - 3s 4ms/step - loss: 11.3992 - val_loss: 3.7479
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 2.3623 - val_loss: 0.9895
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 1.9000 - val_loss: 0.7032
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 1.9483 - val_loss: 0.6894
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 1.7740 - val_loss: 0.7043
Epoch 1/5
195/195 [==============================] - 3s 4ms/step - loss: 288887.1124 - val_loss: 9273.8984
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 159299.0213 - val_loss: 103702.3203
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 106000.8275 - val_loss: 108734.1250
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 101152.5813 - val_loss: 96362.3984
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 101332.2488 - val_loss: 92651.7109
Epoch 1/5
195/195 [==============================] - 3s 4ms/step - loss: 57946.8858 - val_loss: 7179.5469
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 11063.8689 - val_loss: 6582.4004
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 5459.9354 - val_loss: 6161.2886
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 4438.3430 - val_loss: 8423.9580
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 3350.9348 - val_loss: 9283.4736
Epoch 1/5
195/195 [==============================] - 2s 4ms/step - loss: 64508.5843 - val_loss: 14198.4160
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 11904.0326 - val_loss: 2710.7808
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 2748.5283 - val_loss: 2824.1360
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 2514.5690 - val_loss: 2850.3262
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 2252.1726 - val_loss: 3115.8689
Epoch 1/5
195/195 [==============================] - 3s 4ms/step - loss: 5.5322 - val_loss: 2.0038
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 3.3545 - val_loss: 2.5014
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 2.9708 - val_loss: 2.2661
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 3.0467 - val_loss: 1.4595
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 3.2454 - val_loss: 3.1864
Epoch 1/5
195/195 [==============================] - 3s 5ms/step - loss: 524107.4664 - val_loss: 201639.4531
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 338335.2396 - val_loss: 158860.6562
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 213917.1641 - val_loss: 131236.9531
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 147851.4304 - val_loss: 10493.8770
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 91921.0114 - val_loss: 14267.1270
Epoch 1/5
195/195 [==============================] - 8s 4ms/step - loss: 104700.4274 - val_loss: 46962.3828
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 36271.4454 - val_loss: 7074.0283
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 11635.8842 - val_loss: 7324.3828
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 11421.2415 - val_loss: 7338.1011
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 11312.0689 - val_loss: 6852.4214
Epoch 1/5
195/195 [==============================] - 3s 4ms/step - loss: 21623.5376 - val_loss: 9800.3223
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 6702.9368 - val_loss: 9797.9688
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 6054.5557 - val_loss: 9856.6074
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 5999.8479 - val_loss: 9099.5137
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 5735.4621 - val_loss: 9013.6094
Epoch 1/5
195/195 [==============================] - 3s 4ms/step - loss: 7.5672 - val_loss: 4.3287
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 1.0201 - val_loss: 4.0835
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 0.9756 - val_loss: 4.6023
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 0.9116 - val_loss: 3.2968
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 0.9767 - val_loss: 3.2129
Epoch 1/5
195/195 [==============================] - 3s 4ms/step - loss: 2458389.2589 - val_loss: 867205.0000
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 1852895.0089 - val_loss: 276677.6562
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 503290.6060 - val_loss: 617149.1875
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 178635.2850 - val_loss: 736801.1250
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 178838.8390 - val_loss: 715672.3750
Epoch 1/5
195/195 [==============================] - 3s 4ms/step - loss: 82778.6514 - val_loss: 14412.5703
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 20420.2495 - val_loss: 10987.3379
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 11830.3939 - val_loss: 10336.1973
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 11485.6343 - val_loss: 11016.7314
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 11892.2322 - val_loss: 10623.4062
Epoch 1/5
195/195 [==============================] - 3s 4ms/step - loss: 76344.8592 - val_loss: 29675.7969
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 19027.3141 - val_loss: 7708.1348
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 4093.1917 - val_loss: 7450.3511
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 4157.4208 - val_loss: 7509.2197
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 4056.9270 - val_loss: 6989.2749
Epoch 1/5
195/195 [==============================] - 3s 4ms/step - loss: 6.2778 - val_loss: 3.9389
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 2.2533 - val_loss: 6.1296
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 1.5167 - val_loss: 7.7376
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 1.3283 - val_loss: 6.8389
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 1.3598 - val_loss: 7.0241
Epoch 1/5
195/195 [==============================] - 3s 4ms/step - loss: 742676.5179 - val_loss: 190987.5938
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 477861.5403 - val_loss: 83102.7656
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 106062.8286 - val_loss: 240018.8906
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 68934.6304 - val_loss: 233275.1875
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 67057.4847 - val_loss: 249259.8281
Epoch 1/5
195/195 [==============================] - 3s 4ms/step - loss: 152703.4107 - val_loss: 91094.0312
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 70858.2060 - val_loss: 1469.0577
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 1786.7477 - val_loss: 4630.2612
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 1073.3880 - val_loss: 4352.5542
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 972.5255 - val_loss: 4142.9722
Epoch 1/5
195/195 [==============================] - 2s 4ms/step - loss: 21694.9209 - val_loss: 852.8776
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 633.4322 - val_loss: 640.5539
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 250.0851 - val_loss: 595.0905
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 209.6883 - val_loss: 483.5623
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 169.5584 - val_loss: 414.2817
Epoch 1/5
195/195 [==============================] - 3s 4ms/step - loss: 11.9806 - val_loss: 5.5874
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 3.3884 - val_loss: 9.8145
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 2.5301 - val_loss: 12.3391
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 2.4744 - val_loss: 14.6709
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 2.3906 - val_loss: 14.9244
Epoch 1/5
195/195 [==============================] - 3s 4ms/step - loss: 4153653.1735 - val_loss: 245973.1406
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 3147486.2895 - val_loss: 298304.4375
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 920004.5877 - val_loss: 2006818.8750
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 456916.8182 - val_loss: 2276534.2500
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 460389.6584 - val_loss: 2302107.5000

<tensorflow.python.keras.callbacks.History at 0x1955c878d90>

train_predict_CNN_LSTM_Model_pos_x_node_7 = CNN_LSTM_Model_pos_x_node_7.predict(X_training_data_reshaped_cnn_node_7)
test_predict_CNN_LSTM_Model_pos_x_node_7 = CNN_LSTM_Model_pos_x_node_7.predict(X_testing_data_reshaped_cnn_node_7)
train_predict_CNN_LSTM_Model_pos_y_node_7 = CNN_LSTM_Model_pos_y_node_7.predict(X_training_data_reshaped_cnn_node_7)
test_predict_CNN_LSTM_Model_pos_y_node_7 = CNN_LSTM_Model_pos_y_node_7.predict(X_testing_data_reshaped_cnn_node_7)
train_predict_CNN_LSTM_Model_speed_node_7 = CNN_LSTM_Model_speed_node_7.predict(X_training_data_reshaped_cnn_node_7)
test_predict_CNN_LSTM_Model_speed_node_7 = CNN_LSTM_Model_speed_node_7.predict(X_testing_data_reshaped_cnn_node_7)
train_predict_CNN_LSTM_Model_energy_node_7 = CNN_LSTM_Model_energy_node_7.predict(X_training_data_reshaped_cnn_node_7)
test_predict_CNN_LSTM_Model_energy_node_7 = CNN_LSTM_Model_energy_node_7.predict(X_testing_data_reshaped_cnn_node_7)

train_predict_CNN_LSTM_Model_pos_x_node_15 = CNN_LSTM_Model_pos_x_node_15.predict(X_training_data_reshaped_cnn_node_15)
test_predict_CNN_LSTM_Model_pos_x_node_15 = CNN_LSTM_Model_pos_x_node_15.predict(X_testing_data_reshaped_cnn_node_15)
train_predict_CNN_LSTM_Model_pos_y_node_15 = CNN_LSTM_Model_pos_y_node_15.predict(X_training_data_reshaped_cnn_node_15)
test_predict_CNN_LSTM_Model_pos_y_node_15 = CNN_LSTM_Model_pos_y_node_15.predict(X_testing_data_reshaped_cnn_node_15)
train_predict_CNN_LSTM_Model_speed_node_15 = CNN_LSTM_Model_speed_node_15.predict(X_training_data_reshaped_cnn_node_15)
test_predict_CNN_LSTM_Model_speed_node_15 = CNN_LSTM_Model_speed_node_15.predict(X_testing_data_reshaped_cnn_node_15)
train_predict_CNN_LSTM_Model_energy_node_15 = CNN_LSTM_Model_energy_node_15.predict(X_training_data_reshaped_cnn_node_15)
test_predict_CNN_LSTM_Model_energy_node_15 = CNN_LSTM_Model_energy_node_15.predict(X_testing_data_reshaped_cnn_node_15)

train_predict_CNN_LSTM_Model_pos_x_node_24 = CNN_LSTM_Model_pos_x_node_24.predict(X_training_data_reshaped_cnn_node_24)
test_predict_CNN_LSTM_Model_pos_x_node_24 = CNN_LSTM_Model_pos_x_node_24.predict(X_testing_data_reshaped_cnn_node_24)
train_predict_CNN_LSTM_Model_pos_y_node_24 = CNN_LSTM_Model_pos_y_node_24.predict(X_training_data_reshaped_cnn_node_24)
test_predict_CNN_LSTM_Model_pos_y_node_24 = CNN_LSTM_Model_pos_y_node_24.predict(X_testing_data_reshaped_cnn_node_24)
train_predict_CNN_LSTM_Model_speed_node_24 = CNN_LSTM_Model_speed_node_24.predict(X_training_data_reshaped_cnn_node_24)
test_predict_CNN_LSTM_Model_speed_node_24 = CNN_LSTM_Model_speed_node_24.predict(X_testing_data_reshaped_cnn_node_24)
train_predict_CNN_LSTM_Model_energy_node_24 = CNN_LSTM_Model_energy_node_24.predict(X_training_data_reshaped_cnn_node_24)
test_predict_CNN_LSTM_Model_energy_node_24 = CNN_LSTM_Model_energy_node_24.predict(X_testing_data_reshaped_cnn_node_24)

train_predict_CNN_LSTM_Model_pos_x_node_33 = CNN_LSTM_Model_pos_x_node_33.predict(X_training_data_reshaped_cnn_node_33)
test_predict_CNN_LSTM_Model_pos_x_node_33 = CNN_LSTM_Model_pos_x_node_33.predict(X_testing_data_reshaped_cnn_node_33)
train_predict_CNN_LSTM_Model_pos_y_node_33 = CNN_LSTM_Model_pos_y_node_33.predict(X_training_data_reshaped_cnn_node_33)
test_predict_CNN_LSTM_Model_pos_y_node_33 = CNN_LSTM_Model_pos_y_node_33.predict(X_testing_data_reshaped_cnn_node_33)
train_predict_CNN_LSTM_Model_speed_node_33 = CNN_LSTM_Model_speed_node_33.predict(X_training_data_reshaped_cnn_node_33)
test_predict_CNN_LSTM_Model_speed_node_33 = CNN_LSTM_Model_speed_node_33.predict(X_testing_data_reshaped_cnn_node_33)
train_predict_CNN_LSTM_Model_energy_node_33 = CNN_LSTM_Model_energy_node_33.predict(X_training_data_reshaped_cnn_node_33)
test_predict_CNN_LSTM_Model_energy_node_33 = CNN_LSTM_Model_energy_node_33.predict(X_testing_data_reshaped_cnn_node_33)

train_predict_CNN_LSTM_Model_pos_x_node_48 = CNN_LSTM_Model_pos_x_node_48.predict(X_training_data_reshaped_cnn_node_48)
test_predict_CNN_LSTM_Model_pos_x_node_48 = CNN_LSTM_Model_pos_x_node_48.predict(X_testing_data_reshaped_cnn_node_48)
train_predict_CNN_LSTM_Model_pos_y_node_48 = CNN_LSTM_Model_pos_y_node_48.predict(X_training_data_reshaped_cnn_node_48)
test_predict_CNN_LSTM_Model_pos_y_node_48 = CNN_LSTM_Model_pos_y_node_48.predict(X_testing_data_reshaped_cnn_node_48)
train_predict_CNN_LSTM_Model_speed_node_48 = CNN_LSTM_Model_speed_node_48.predict(X_training_data_reshaped_cnn_node_48)
test_predict_CNN_LSTM_Model_speed_node_48 = CNN_LSTM_Model_speed_node_48.predict(X_testing_data_reshaped_cnn_node_48)
train_predict_CNN_LSTM_Model_energy_node_48 = CNN_LSTM_Model_energy_node_48.predict(X_training_data_reshaped_cnn_node_48)
test_predict_CNN_LSTM_Model_energy_node_48 = CNN_LSTM_Model_energy_node_48.predict(X_testing_data_reshaped_cnn_node_48)

RMSE

print("\n\nRMSE on Training Data by CNN LSTM: ")
print("======================================\n\n")

print("\n\nRMSE of Node 7: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_7,train_predict_CNN_LSTM_Model_pos_x_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_7,train_predict_CNN_LSTM_Model_pos_y_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_7,train_predict_CNN_LSTM_Model_speed_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_7,train_predict_CNN_LSTM_Model_energy_node_7)))
      
print("\n\nRMSE of Node 15: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_15,train_predict_CNN_LSTM_Model_pos_x_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_15,train_predict_CNN_LSTM_Model_pos_y_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_15,train_predict_CNN_LSTM_Model_speed_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_15,train_predict_CNN_LSTM_Model_energy_node_15)))
      
print("\n\nRMSE of Node 24: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_24,train_predict_CNN_LSTM_Model_pos_x_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_24,train_predict_CNN_LSTM_Model_pos_y_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_24,train_predict_CNN_LSTM_Model_speed_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_24,train_predict_CNN_LSTM_Model_energy_node_24)))

print("\n\nRMSE of Node 33: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_33,train_predict_CNN_LSTM_Model_pos_x_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_33,train_predict_CNN_LSTM_Model_pos_y_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_33,train_predict_CNN_LSTM_Model_speed_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_33,train_predict_CNN_LSTM_Model_energy_node_33)))
      
print("\n\nRMSE of Node 48: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_48,train_predict_CNN_LSTM_Model_pos_x_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_48,train_predict_CNN_LSTM_Model_pos_y_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_48,train_predict_CNN_LSTM_Model_speed_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_48,train_predict_CNN_LSTM_Model_energy_node_48)))

print("\n\nRMSE on Testing Data by CNN LSTM: ")
print("=====================================\n\n")
      
print("\n\nRMSE of Node 7: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_CNN_LSTM_Model_pos_x_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_CNN_LSTM_Model_pos_y_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_CNN_LSTM_Model_speed_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_CNN_LSTM_Model_energy_node_7)))
      
print("\n\nRMSE of Node 15: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_CNN_LSTM_Model_pos_x_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_CNN_LSTM_Model_pos_y_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_CNN_LSTM_Model_speed_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_CNN_LSTM_Model_energy_node_15)))
     
print("\n\nRMSE of Node 24: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_CNN_LSTM_Model_pos_x_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_24,test_predict_CNN_LSTM_Model_pos_y_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_CNN_LSTM_Model_speed_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_CNN_LSTM_Model_energy_node_24)))
      
print("\n\nRMSE of Node 33: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_CNN_LSTM_Model_pos_x_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_CNN_LSTM_Model_pos_y_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_CNN_LSTM_Model_speed_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_CNN_LSTM_Model_energy_node_33)))
      
print("\n\nRMSE of Node 48: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_CNN_LSTM_Model_pos_x_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_CNN_LSTM_Model_pos_y_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_CNN_LSTM_Model_speed_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_CNN_LSTM_Model_energy_node_48)))

RMSE on Training Data by CNN LSTM: 
======================================




RMSE of Node 7: 
======================================


44.27740260979573
85.98844216927282
1.3822038122304854
314.91651043357507


RMSE of Node 15: 
======================================


49.82256958992373
46.06200309055076
1.7817174242640255
305.12781177145473


RMSE of Node 24: 
======================================


108.32741654497529
75.94358036109008
0.9826718584483183
421.7861565219292


RMSE of Node 33: 
======================================


107.71871353117449
61.1521486886184
1.1375845089767747
259.37102207162746


RMSE of Node 48: 
======================================


30.44224059411331
12.46263549416015
1.5621824086215996
683.6896039399132


RMSE on Testing Data by CNN LSTM: 
=====================================




RMSE of Node 7: 
======================================


41.42521368851659
53.92020967961218
0.8392285797671369
304.38738333529415


RMSE of Node 15: 
======================================


96.3507495509225
55.81996695241883
1.785049553037206
119.44507918527674


RMSE of Node 24: 
======================================


82.77935328590216
94.94003132283116
1.7924455355735254
845.9742692550271


RMSE of Node 33: 
======================================


103.06990579867387
83.60188222900314
2.65029331668349
499.25925813945594


RMSE of Node 48: 
======================================


64.3659207800162
20.353913128691545
3.863205652102362
1517.2697593171383

Graph

print("\n\nGraph of Node 7: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_7)
plt.plot(test_predict_CNN_LSTM_Model_pos_x_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_7)
plt.plot(test_predict_CNN_LSTM_Model_pos_y_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_7)
plt.plot(test_predict_CNN_LSTM_Model_speed_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_7)
plt.plot(test_predict_CNN_LSTM_Model_energy_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 15: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_15)
plt.plot(test_predict_CNN_LSTM_Model_pos_x_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_15)
plt.plot(test_predict_CNN_LSTM_Model_pos_y_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_15)
plt.plot(test_predict_CNN_LSTM_Model_speed_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_15)
plt.plot(test_predict_CNN_LSTM_Model_energy_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 24: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_24)
plt.plot(test_predict_CNN_LSTM_Model_pos_x_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_24)
plt.plot(test_predict_CNN_LSTM_Model_pos_y_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_24)
plt.plot(test_predict_CNN_LSTM_Model_speed_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_24)
plt.plot(test_predict_CNN_LSTM_Model_energy_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 33: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_33)
plt.plot(test_predict_CNN_LSTM_Model_pos_x_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_33)
plt.plot(test_predict_CNN_LSTM_Model_pos_y_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_33)
plt.plot(test_predict_CNN_LSTM_Model_speed_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_33)
plt.plot(test_predict_CNN_LSTM_Model_energy_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 48: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_48)
plt.plot(test_predict_CNN_LSTM_Model_pos_x_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_48)
plt.plot(test_predict_CNN_LSTM_Model_pos_y_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_48)
plt.plot(test_predict_CNN_LSTM_Model_speed_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_48)
plt.plot(test_predict_CNN_LSTM_Model_energy_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

Graph of Node 7: 
======================================

Graph of Node 15: 
======================================

Graph of Node 24: 
======================================

Graph of Node 33: 
======================================

Graph of Node 48: 
======================================

============================

LSTM

============================

LSTM_Model_pos_x_node_7 = Sequential()
LSTM_Model_pos_x_node_7.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_pos_x_node_7.add(Dense(1))
LSTM_Model_pos_x_node_7.compile(loss='mean_squared_error',optimizer='adam')
LSTM_Model_pos_y_node_7 = Sequential()
LSTM_Model_pos_y_node_7.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_pos_y_node_7.add(Dense(1))
LSTM_Model_pos_y_node_7.compile(loss='mean_squared_error',optimizer='adam')
LSTM_Model_speed_node_7 = Sequential()
LSTM_Model_speed_node_7.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_speed_node_7.add(Dense(1))
LSTM_Model_speed_node_7.compile(loss='mean_squared_error',optimizer='adam')
LSTM_Model_energy_node_7 = Sequential()
LSTM_Model_energy_node_7.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_energy_node_7.add(Dense(1))
LSTM_Model_energy_node_7.compile(loss='mean_squared_error',optimizer='adam')

LSTM_Model_pos_x_node_15 = Sequential()
LSTM_Model_pos_x_node_15.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_pos_x_node_15.add(Dense(1))
LSTM_Model_pos_x_node_15.compile(loss='mean_squared_error',optimizer='adam')
LSTM_Model_pos_y_node_15 = Sequential()
LSTM_Model_pos_y_node_15.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_pos_y_node_15.add(Dense(1))
LSTM_Model_pos_y_node_15.compile(loss='mean_squared_error',optimizer='adam')
LSTM_Model_speed_node_15 = Sequential()
LSTM_Model_speed_node_15.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_speed_node_15.add(Dense(1))
LSTM_Model_speed_node_15.compile(loss='mean_squared_error',optimizer='adam')
LSTM_Model_energy_node_15 = Sequential()
LSTM_Model_energy_node_15.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_energy_node_15.add(Dense(1))
LSTM_Model_energy_node_15.compile(loss='mean_squared_error',optimizer='adam')

LSTM_Model_pos_x_node_24 = Sequential()
LSTM_Model_pos_x_node_24.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_pos_x_node_24.add(Dense(1))
LSTM_Model_pos_x_node_24.compile(loss='mean_squared_error',optimizer='adam')
LSTM_Model_pos_y_node_24 = Sequential()
LSTM_Model_pos_y_node_24.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_pos_y_node_24.add(Dense(1))
LSTM_Model_pos_y_node_24.compile(loss='mean_squared_error',optimizer='adam')
LSTM_Model_speed_node_24 = Sequential()
LSTM_Model_speed_node_24.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_speed_node_24.add(Dense(1))
LSTM_Model_speed_node_24.compile(loss='mean_squared_error',optimizer='adam')
LSTM_Model_energy_node_24 = Sequential()
LSTM_Model_energy_node_24.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_energy_node_24.add(Dense(1))
LSTM_Model_energy_node_24.compile(loss='mean_squared_error',optimizer='adam')

LSTM_Model_pos_x_node_33 = Sequential()
LSTM_Model_pos_x_node_33.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_pos_x_node_33.add(Dense(1))
LSTM_Model_pos_x_node_33.compile(loss='mean_squared_error',optimizer='adam')
LSTM_Model_pos_y_node_33 = Sequential()
LSTM_Model_pos_y_node_33.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_pos_y_node_33.add(Dense(1))
LSTM_Model_pos_y_node_33.compile(loss='mean_squared_error',optimizer='adam')
LSTM_Model_speed_node_33 = Sequential()
LSTM_Model_speed_node_33.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_speed_node_33.add(Dense(1))
LSTM_Model_speed_node_33.compile(loss='mean_squared_error',optimizer='adam')
LSTM_Model_energy_node_33 = Sequential()
LSTM_Model_energy_node_33.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_energy_node_33.add(Dense(1))
LSTM_Model_energy_node_33.compile(loss='mean_squared_error',optimizer='adam')

LSTM_Model_pos_x_node_48 = Sequential()
LSTM_Model_pos_x_node_48.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_pos_x_node_48.add(Dense(1))
LSTM_Model_pos_x_node_48.compile(loss='mean_squared_error',optimizer='adam')
LSTM_Model_pos_y_node_48 = Sequential()
LSTM_Model_pos_y_node_48.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_pos_y_node_48.add(Dense(1))
LSTM_Model_pos_y_node_48.compile(loss='mean_squared_error',optimizer='adam')
LSTM_Model_speed_node_48 = Sequential()
LSTM_Model_speed_node_48.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_speed_node_48.add(Dense(1))
LSTM_Model_speed_node_48.compile(loss='mean_squared_error',optimizer='adam')
LSTM_Model_energy_node_48 = Sequential()
LSTM_Model_energy_node_48.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_energy_node_48.add(Dense(1))
LSTM_Model_energy_node_48.compile(loss='mean_squared_error',optimizer='adam')

LSTM_Model_pos_x_node_7.fit(X_training_data_reshaped_node_7,y_training_data_pos_x_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_pos_x_node_7),epochs=5,batch_size=10,verbose=1)
LSTM_Model_pos_y_node_7.fit(X_training_data_reshaped_node_7,y_training_data_pos_y_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_pos_y_node_7),epochs=5,batch_size=10,verbose=1)
LSTM_Model_speed_node_7.fit(X_training_data_reshaped_node_7,y_training_data_speed_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_speed_node_7),epochs=5,batch_size=10,verbose=1)
LSTM_Model_energy_node_7.fit(X_training_data_reshaped_node_7,y_training_data_energy_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_energy_node_7),epochs=5,batch_size=10,verbose=1)

LSTM_Model_pos_x_node_15.fit(X_training_data_reshaped_node_15,y_training_data_pos_x_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_pos_x_node_15),epochs=5,batch_size=10,verbose=1)
LSTM_Model_pos_y_node_15.fit(X_training_data_reshaped_node_15,y_training_data_pos_y_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_pos_y_node_15),epochs=5,batch_size=10,verbose=1)
LSTM_Model_speed_node_15.fit(X_training_data_reshaped_node_15,y_training_data_speed_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_speed_node_15),epochs=5,batch_size=10,verbose=1)
LSTM_Model_energy_node_15.fit(X_training_data_reshaped_node_15,y_training_data_energy_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_energy_node_15),epochs=5,batch_size=10,verbose=1)

LSTM_Model_pos_x_node_24.fit(X_training_data_reshaped_node_24,y_training_data_pos_x_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_pos_x_node_24),epochs=5,batch_size=10,verbose=1)
LSTM_Model_pos_y_node_24.fit(X_training_data_reshaped_node_24,y_training_data_pos_y_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_pos_y_node_24),epochs=5,batch_size=10,verbose=1)
LSTM_Model_speed_node_24.fit(X_training_data_reshaped_node_24,y_training_data_speed_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_speed_node_24),epochs=5,batch_size=10,verbose=1)
LSTM_Model_energy_node_24.fit(X_training_data_reshaped_node_24,y_training_data_energy_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_energy_node_24),epochs=5,batch_size=10,verbose=1)

LSTM_Model_pos_x_node_33.fit(X_training_data_reshaped_node_33,y_training_data_pos_x_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_pos_x_node_33),epochs=5,batch_size=10,verbose=1)
LSTM_Model_pos_y_node_33.fit(X_training_data_reshaped_node_33,y_training_data_pos_y_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_pos_y_node_33),epochs=5,batch_size=10,verbose=1)
LSTM_Model_speed_node_33.fit(X_training_data_reshaped_node_33,y_training_data_speed_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_speed_node_33),epochs=5,batch_size=10,verbose=1)
LSTM_Model_energy_node_33.fit(X_training_data_reshaped_node_33,y_training_data_energy_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_energy_node_33),epochs=5,batch_size=10,verbose=1)

LSTM_Model_pos_x_node_48.fit(X_training_data_reshaped_node_48,y_training_data_pos_x_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_pos_x_node_48),epochs=5,batch_size=10,verbose=1)
LSTM_Model_pos_y_node_48.fit(X_training_data_reshaped_node_48,y_training_data_pos_y_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_pos_y_node_48),epochs=5,batch_size=10,verbose=1)
LSTM_Model_speed_node_48.fit(X_training_data_reshaped_node_48,y_training_data_speed_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_speed_node_48),epochs=5,batch_size=10,verbose=1)
LSTM_Model_energy_node_48.fit(X_training_data_reshaped_node_48,y_training_data_energy_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_energy_node_48),epochs=5,batch_size=10,verbose=1)

Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 35182.6694 - val_loss: 24429.8555
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 30740.9836 - val_loss: 21501.4004
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 27386.2439 - val_loss: 19056.5898
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 23749.0915 - val_loss: 16918.5371
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 21274.1474 - val_loss: 15038.0869
Epoch 1/5
195/195 [==============================] - 4s 8ms/step - loss: 43985.8622 - val_loss: 22304.0488
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 37979.5275 - val_loss: 19242.8203
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 35827.0654 - val_loss: 16710.5156
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 31942.3797 - val_loss: 14490.9531
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 28633.0828 - val_loss: 12528.5264
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 11.3619 - val_loss: 9.5855
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 3.7902 - val_loss: 3.5774
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 0.9898 - val_loss: 0.6237
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 0.3182 - val_loss: 0.6054
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 0.3519 - val_loss: 0.4569
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 291540.0808 - val_loss: 1318.8726
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 261244.9174 - val_loss: 1676.5048
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 272830.8835 - val_loss: 2211.7000
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 255749.5774 - val_loss: 2916.8225
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 251041.2866 - val_loss: 3781.1055
Epoch 1/5
195/195 [==============================] - 11s 8ms/step - loss: 59813.0503 - val_loss: 33103.5312
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 50971.0870 - val_loss: 29334.9824
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 47142.3497 - val_loss: 26127.1992
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 42604.3245 - val_loss: 23272.9434
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 39292.3979 - val_loss: 20680.1113
Epoch 1/5
195/195 [==============================] - 4s 8ms/step - loss: 66279.8005 - val_loss: 45971.4414
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 55193.5110 - val_loss: 41278.4219
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 50086.7369 - val_loss: 37247.1758
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 45345.3784 - val_loss: 33585.2227
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 42002.3566 - val_loss: 30239.9492
Epoch 1/5
195/195 [==============================] - 4s 8ms/step - loss: 6.6543 - val_loss: 6.0010
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 2.9416 - val_loss: 0.6327
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 0.1998 - val_loss: 0.5288
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 0.2241 - val_loss: 0.4368
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 0.1489 - val_loss: 0.5380
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 536140.9523 - val_loss: 249244.1406
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 484845.8940 - val_loss: 243371.0156
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 469993.9294 - val_loss: 238164.3906
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 454211.6398 - val_loss: 233384.0000
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 433587.7942 - val_loss: 228884.0938
Epoch 1/5
195/195 [==============================] - 3s 6ms/step - loss: 104099.3585 - val_loss: 85993.7188
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 92954.4725 - val_loss: 79976.2578
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 87453.0656 - val_loss: 74732.8906
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 82116.6186 - val_loss: 69917.8984
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 76163.9015 - val_loss: 65444.8438
Epoch 1/5
195/195 [==============================] - 3s 6ms/step - loss: 22461.9986 - val_loss: 17519.4375
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 16596.0688 - val_loss: 15433.6035
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 15110.3606 - val_loss: 13817.2930
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 13400.2462 - val_loss: 12490.9131
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 12179.2534 - val_loss: 11379.1738
Epoch 1/5
195/195 [==============================] - 3s 6ms/step - loss: 7.4695 - val_loss: 7.0477
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 1.4245 - val_loss: 5.9705
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 1.0566 - val_loss: 1.8649
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 0.2270 - val_loss: 1.2965
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 0.1320 - val_loss: 1.4979
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 2446364.8202 - val_loss: 1038951.2500
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 2401367.2793 - val_loss: 1019710.3125
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 2343997.1531 - val_loss: 1002041.0625
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 2294950.0969 - val_loss: 985158.3125
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 2346664.7621 - val_loss: 968737.6875
Epoch 1/5
195/195 [==============================] - 3s 6ms/step - loss: 83741.9201 - val_loss: 52719.0117
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 75595.6241 - val_loss: 47987.8633
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 68269.5701 - val_loss: 43919.5977
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 63555.1075 - val_loss: 40209.8281
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 61847.9472 - val_loss: 36812.2734
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 77468.5371 - val_loss: 65267.9805
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 68126.3045 - val_loss: 59999.3242
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 62550.3760 - val_loss: 55408.0898
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 58133.9963 - val_loss: 51220.7773
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 53647.6385 - val_loss: 47336.2500
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 6.6522 - val_loss: 2.1142
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 3.3962 - val_loss: 1.3708
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 0.8517 - val_loss: 1.2348
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 0.1970 - val_loss: 0.8768
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 0.1792 - val_loss: 1.1516
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 758419.3925 - val_loss: 259180.2344
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 722424.5188 - val_loss: 249628.7656
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 694539.9072 - val_loss: 241160.2188
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 708839.1298 - val_loss: 233215.8438
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 670325.7379 - val_loss: 225654.9062
Epoch 1/5
195/195 [==============================] - 3s 6ms/step - loss: 153450.9161 - val_loss: 130936.5625
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 137768.4483 - val_loss: 122710.9453
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 129965.2486 - val_loss: 115467.8359
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 122979.4569 - val_loss: 108731.0781
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 116203.9556 - val_loss: 102366.5938
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 22718.0578 - val_loss: 17438.2168
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 17104.5666 - val_loss: 14610.4551
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 14396.2013 - val_loss: 12309.4248
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 12158.5387 - val_loss: 10334.0947
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 10241.1941 - val_loss: 8622.0088
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 10.6369 - val_loss: 7.3094
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 4.2257 - val_loss: 10.4961
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 3.3376 - val_loss: 9.6487
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 1.3984 - val_loss: 3.5596
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 0.3447 - val_loss: 1.8267
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 4157306.6390 - val_loss: 408078.4062
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 4040658.8661 - val_loss: 393794.8438
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 4076566.4439 - val_loss: 380918.1875
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 4004144.1263 - val_loss: 368594.1875
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 4080549.2717 - val_loss: 356714.1250

<tensorflow.python.keras.callbacks.History at 0x195a37135e0>

train_predict_LSTM_Model_pos_x_node_7 = LSTM_Model_pos_x_node_7.predict(X_training_data_reshaped_node_7)
test_predict_LSTM_Model_pos_x_node_7 = LSTM_Model_pos_x_node_7.predict(X_testing_data_reshaped_node_7)
train_predict_LSTM_Model_pos_y_node_7 = LSTM_Model_pos_y_node_7.predict(X_training_data_reshaped_node_7)
test_predict_LSTM_Model_pos_y_node_7 = LSTM_Model_pos_y_node_7.predict(X_testing_data_reshaped_node_7)
train_predict_LSTM_Model_speed_node_7 = LSTM_Model_speed_node_7.predict(X_training_data_reshaped_node_7)
test_predict_LSTM_Model_speed_node_7 = LSTM_Model_speed_node_7.predict(X_testing_data_reshaped_node_7)
train_predict_LSTM_Model_energy_node_7 = LSTM_Model_energy_node_7.predict(X_training_data_reshaped_node_7)
test_predict_LSTM_Model_energy_node_7 = LSTM_Model_energy_node_7.predict(X_testing_data_reshaped_node_7)

train_predict_LSTM_Model_pos_x_node_15 = LSTM_Model_pos_x_node_15.predict(X_training_data_reshaped_node_15)
test_predict_LSTM_Model_pos_x_node_15 = LSTM_Model_pos_x_node_15.predict(X_testing_data_reshaped_node_15)
train_predict_LSTM_Model_pos_y_node_15 = LSTM_Model_pos_y_node_15.predict(X_training_data_reshaped_node_15)
test_predict_LSTM_Model_pos_y_node_15 = LSTM_Model_pos_y_node_15.predict(X_testing_data_reshaped_node_15)
train_predict_LSTM_Model_speed_node_15 = LSTM_Model_speed_node_15.predict(X_training_data_reshaped_node_15)
test_predict_LSTM_Model_speed_node_15 = LSTM_Model_speed_node_15.predict(X_testing_data_reshaped_node_15)
train_predict_LSTM_Model_energy_node_15 = LSTM_Model_energy_node_15.predict(X_training_data_reshaped_node_15)
test_predict_LSTM_Model_energy_node_15 = LSTM_Model_energy_node_15.predict(X_testing_data_reshaped_node_15)

train_predict_LSTM_Model_pos_x_node_24 = LSTM_Model_pos_x_node_24.predict(X_training_data_reshaped_node_24)
test_predict_LSTM_Model_pos_x_node_24 = LSTM_Model_pos_x_node_24.predict(X_testing_data_reshaped_node_24)
train_predict_LSTM_Model_pos_y_node_24 = LSTM_Model_pos_y_node_24.predict(X_training_data_reshaped_node_24)
test_predict_LSTM_Model_pos_y_node_24 = LSTM_Model_pos_y_node_24.predict(X_testing_data_reshaped_node_24)
train_predict_LSTM_Model_speed_node_24 = LSTM_Model_speed_node_24.predict(X_training_data_reshaped_node_24)
test_predict_LSTM_Model_speed_node_24 = LSTM_Model_speed_node_24.predict(X_testing_data_reshaped_node_24)
train_predict_LSTM_Model_energy_node_24 = LSTM_Model_energy_node_24.predict(X_training_data_reshaped_node_24)
test_predict_LSTM_Model_energy_node_24 = LSTM_Model_energy_node_24.predict(X_testing_data_reshaped_node_24)

train_predict_LSTM_Model_pos_x_node_33 = LSTM_Model_pos_x_node_33.predict(X_training_data_reshaped_node_33)
test_predict_LSTM_Model_pos_x_node_33 = LSTM_Model_pos_x_node_33.predict(X_testing_data_reshaped_node_33)
train_predict_LSTM_Model_pos_y_node_33 = LSTM_Model_pos_y_node_33.predict(X_training_data_reshaped_node_33)
test_predict_LSTM_Model_pos_y_node_33 = LSTM_Model_pos_y_node_33.predict(X_testing_data_reshaped_node_33)
train_predict_LSTM_Model_speed_node_33 = LSTM_Model_speed_node_33.predict(X_training_data_reshaped_node_33)
test_predict_LSTM_Model_speed_node_33 = LSTM_Model_speed_node_33.predict(X_testing_data_reshaped_node_33)
train_predict_LSTM_Model_energy_node_33 = LSTM_Model_energy_node_33.predict(X_training_data_reshaped_node_33)
test_predict_LSTM_Model_energy_node_33 = LSTM_Model_energy_node_33.predict(X_testing_data_reshaped_node_33)

train_predict_LSTM_Model_pos_x_node_48 = LSTM_Model_pos_x_node_48.predict(X_training_data_reshaped_node_48)
test_predict_LSTM_Model_pos_x_node_48 = LSTM_Model_pos_x_node_48.predict(X_testing_data_reshaped_node_48)
train_predict_LSTM_Model_pos_y_node_48 = LSTM_Model_pos_y_node_48.predict(X_training_data_reshaped_node_48)
test_predict_LSTM_Model_pos_y_node_48 = LSTM_Model_pos_y_node_48.predict(X_testing_data_reshaped_node_48)
train_predict_LSTM_Model_speed_node_48 = LSTM_Model_speed_node_48.predict(X_training_data_reshaped_node_48)
test_predict_LSTM_Model_speed_node_48 = LSTM_Model_speed_node_48.predict(X_testing_data_reshaped_node_48)
train_predict_LSTM_Model_energy_node_48 = LSTM_Model_energy_node_48.predict(X_training_data_reshaped_node_48)
test_predict_LSTM_Model_energy_node_48 = LSTM_Model_energy_node_48.predict(X_testing_data_reshaped_node_48)

RMSE

print("\n\nRMSE on Training Data by LSTM: ")
print("======================================\n\n")

print("\n\nRMSE of Node 7: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_7,train_predict_LSTM_Model_pos_x_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_7,train_predict_LSTM_Model_pos_y_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_7,train_predict_LSTM_Model_speed_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_7,train_predict_LSTM_Model_energy_node_7)))
      
print("\n\nRMSE of Node 15: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_15,train_predict_LSTM_Model_pos_x_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_15,train_predict_LSTM_Model_pos_y_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_15,train_predict_LSTM_Model_speed_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_15,train_predict_LSTM_Model_energy_node_15)))
      
print("\n\nRMSE of Node 24: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_24,train_predict_LSTM_Model_pos_x_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_24,train_predict_LSTM_Model_pos_y_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_24,train_predict_LSTM_Model_speed_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_24,train_predict_LSTM_Model_energy_node_24)))

print("\n\nRMSE of Node 33: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_33,train_predict_LSTM_Model_pos_x_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_33,train_predict_LSTM_Model_pos_y_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_33,train_predict_LSTM_Model_speed_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_33,train_predict_LSTM_Model_energy_node_33)))
      
print("\n\nRMSE of Node 48: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_48,train_predict_LSTM_Model_pos_x_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_48,train_predict_LSTM_Model_pos_y_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_48,train_predict_LSTM_Model_speed_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_48,train_predict_LSTM_Model_energy_node_48)))

print("\n\nRMSE on Testing Data by LSTM: ")
print("=====================================\n\n")
      
print("\n\nRMSE of Node 7: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_LSTM_Model_pos_x_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_LSTM_Model_pos_y_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_LSTM_Model_speed_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_LSTM_Model_energy_node_7)))
      
print("\n\nRMSE of Node 15: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_LSTM_Model_pos_x_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_LSTM_Model_pos_y_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_LSTM_Model_speed_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_LSTM_Model_energy_node_15)))
     
print("\n\nRMSE of Node 24: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_LSTM_Model_pos_x_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_24,test_predict_LSTM_Model_pos_y_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_LSTM_Model_speed_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_LSTM_Model_energy_node_24)))
      
print("\n\nRMSE of Node 33: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_LSTM_Model_pos_x_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_LSTM_Model_pos_y_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_LSTM_Model_speed_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_LSTM_Model_energy_node_33)))
      
print("\n\nRMSE of Node 48: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_LSTM_Model_pos_x_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_LSTM_Model_pos_y_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_LSTM_Model_speed_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_LSTM_Model_energy_node_48)))

RMSE on Training Data by LSTM: 
======================================




RMSE of Node 7: 
======================================


140.99542271102305
164.05154596001034
0.5143053112011458
493.20380148496633


RMSE of Node 15: 
======================================


192.7593754202154
199.34011802129592
0.4508044410180804
675.5754523927812


RMSE of Node 24: 
======================================


269.1292482623632
104.17652685977014
0.37216207192664663
1511.3795232618725


RMSE of Node 33: 
======================================


238.03939440797305
225.1499469515692
0.41069827920017676
809.7495745913774


RMSE of Node 48: 
======================================


333.2267088208572
94.47078273879096
0.37880104836639333
1991.7495049072038


RMSE on Testing Data by LSTM: 
=====================================




RMSE of Node 7: 
======================================


122.62988736273873
111.93091939923399
0.6759420687072014
61.49070066779251


RMSE of Node 15: 
======================================


143.80582473763488
173.89636892905497
0.7334628834121973
478.41840458462974


RMSE of Node 24: 
======================================


255.82188337992102
106.67321693285228
1.2239059435773598
984.2447765291922


RMSE of Node 33: 
======================================


191.86525172717202
217.56895903489925
1.0731063914884176
475.03147964115055


RMSE of Node 48: 
======================================


319.9478090170709
92.85477723599958
1.351553273418894
597.2554842870163

Graph

print("\n\nGraph of Node 7: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_7)
plt.plot(test_predict_LSTM_Model_pos_x_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_7)
plt.plot(test_predict_LSTM_Model_pos_y_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_7)
plt.plot(test_predict_LSTM_Model_speed_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_7)
plt.plot(test_predict_LSTM_Model_energy_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 15: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_15)
plt.plot(test_predict_LSTM_Model_pos_x_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_15)
plt.plot(test_predict_LSTM_Model_pos_y_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_15)
plt.plot(test_predict_LSTM_Model_speed_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_15)
plt.plot(test_predict_LSTM_Model_energy_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 24: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_24)
plt.plot(test_predict_LSTM_Model_pos_x_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_24)
plt.plot(test_predict_LSTM_Model_pos_y_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_24)
plt.plot(test_predict_LSTM_Model_speed_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_24)
plt.plot(test_predict_LSTM_Model_energy_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 33: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_33)
plt.plot(test_predict_LSTM_Model_pos_x_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_33)
plt.plot(test_predict_LSTM_Model_pos_y_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_33)
plt.plot(test_predict_LSTM_Model_speed_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_33)
plt.plot(test_predict_LSTM_Model_energy_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 48: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_48)
plt.plot(test_predict_LSTM_Model_pos_x_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_48)
plt.plot(test_predict_LSTM_Model_pos_y_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_48)
plt.plot(test_predict_LSTM_Model_speed_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_48)
plt.plot(test_predict_LSTM_Model_energy_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

Graph of Node 7: 
======================================

Graph of Node 15: 
======================================

Graph of Node 24: 
======================================

Graph of Node 33: 
======================================

Graph of Node 48: 
======================================

======================================

Bi-directional LSTM

======================================

BiDirectonal_LSTM_Model_pos_x_node_7 = Sequential()
BiDirectonal_LSTM_Model_pos_x_node_7.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_pos_x_node_7.add(Dense(1))
BiDirectonal_LSTM_Model_pos_x_node_7.compile(loss='mean_squared_error',optimizer='adam')
BiDirectonal_LSTM_Model_pos_y_node_7 = Sequential()
BiDirectonal_LSTM_Model_pos_y_node_7.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_pos_y_node_7.add(Dense(1))
BiDirectonal_LSTM_Model_pos_y_node_7.compile(loss='mean_squared_error',optimizer='adam')
BiDirectonal_LSTM_Model_speed_node_7 = Sequential()
BiDirectonal_LSTM_Model_speed_node_7.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_speed_node_7.add(Dense(1))
BiDirectonal_LSTM_Model_speed_node_7.compile(loss='mean_squared_error',optimizer='adam')
BiDirectonal_LSTM_Model_energy_node_7 = Sequential()
BiDirectonal_LSTM_Model_energy_node_7.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_energy_node_7.add(Dense(1))
BiDirectonal_LSTM_Model_energy_node_7.compile(loss='mean_squared_error',optimizer='adam')

BiDirectonal_LSTM_Model_pos_x_node_15 = Sequential()
BiDirectonal_LSTM_Model_pos_x_node_15.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_pos_x_node_15.add(Dense(1))
BiDirectonal_LSTM_Model_pos_x_node_15.compile(loss='mean_squared_error',optimizer='adam')
BiDirectonal_LSTM_Model_pos_y_node_15 = Sequential()
BiDirectonal_LSTM_Model_pos_y_node_15.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_pos_y_node_15.add(Dense(1))
BiDirectonal_LSTM_Model_pos_y_node_15.compile(loss='mean_squared_error',optimizer='adam')
BiDirectonal_LSTM_Model_speed_node_15 = Sequential()
BiDirectonal_LSTM_Model_speed_node_15.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_speed_node_15.add(Dense(1))
BiDirectonal_LSTM_Model_speed_node_15.compile(loss='mean_squared_error',optimizer='adam')
BiDirectonal_LSTM_Model_energy_node_15 = Sequential()
BiDirectonal_LSTM_Model_energy_node_15.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_energy_node_15.add(Dense(1))
BiDirectonal_LSTM_Model_energy_node_15.compile(loss='mean_squared_error',optimizer='adam')

BiDirectonal_LSTM_Model_pos_x_node_24 = Sequential()
BiDirectonal_LSTM_Model_pos_x_node_24.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_pos_x_node_24.add(Dense(1))
BiDirectonal_LSTM_Model_pos_x_node_24.compile(loss='mean_squared_error',optimizer='adam')
BiDirectonal_LSTM_Model_pos_y_node_24 = Sequential()
BiDirectonal_LSTM_Model_pos_y_node_24.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_pos_y_node_24.add(Dense(1))
BiDirectonal_LSTM_Model_pos_y_node_24.compile(loss='mean_squared_error',optimizer='adam')
BiDirectonal_LSTM_Model_speed_node_24 = Sequential()
BiDirectonal_LSTM_Model_speed_node_24.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_speed_node_24.add(Dense(1))
BiDirectonal_LSTM_Model_speed_node_24.compile(loss='mean_squared_error',optimizer='adam')
BiDirectonal_LSTM_Model_energy_node_24 = Sequential()
BiDirectonal_LSTM_Model_energy_node_24.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_energy_node_24.add(Dense(1))
BiDirectonal_LSTM_Model_energy_node_24.compile(loss='mean_squared_error',optimizer='adam')

BiDirectonal_LSTM_Model_pos_x_node_33 = Sequential()
BiDirectonal_LSTM_Model_pos_x_node_33.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_pos_x_node_33.add(Dense(1))
BiDirectonal_LSTM_Model_pos_x_node_33.compile(loss='mean_squared_error',optimizer='adam')
BiDirectonal_LSTM_Model_pos_y_node_33 = Sequential()
BiDirectonal_LSTM_Model_pos_y_node_33.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_pos_y_node_33.add(Dense(1))
BiDirectonal_LSTM_Model_pos_y_node_33.compile(loss='mean_squared_error',optimizer='adam')
BiDirectonal_LSTM_Model_speed_node_33 = Sequential()
BiDirectonal_LSTM_Model_speed_node_33.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_speed_node_33.add(Dense(1))
BiDirectonal_LSTM_Model_speed_node_33.compile(loss='mean_squared_error',optimizer='adam')
BiDirectonal_LSTM_Model_energy_node_33 = Sequential()
BiDirectonal_LSTM_Model_energy_node_33.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_energy_node_33.add(Dense(1))
BiDirectonal_LSTM_Model_energy_node_33.compile(loss='mean_squared_error',optimizer='adam')

BiDirectonal_LSTM_Model_pos_x_node_48 = Sequential()
BiDirectonal_LSTM_Model_pos_x_node_48.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_pos_x_node_48.add(Dense(1))
BiDirectonal_LSTM_Model_pos_x_node_48.compile(loss='mean_squared_error',optimizer='adam')
BiDirectonal_LSTM_Model_pos_y_node_48 = Sequential()
BiDirectonal_LSTM_Model_pos_y_node_48.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_pos_y_node_48.add(Dense(1))
BiDirectonal_LSTM_Model_pos_y_node_48.compile(loss='mean_squared_error',optimizer='adam')
BiDirectonal_LSTM_Model_speed_node_48 = Sequential()
BiDirectonal_LSTM_Model_speed_node_48.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_speed_node_48.add(Dense(1))
BiDirectonal_LSTM_Model_speed_node_48.compile(loss='mean_squared_error',optimizer='adam')
BiDirectonal_LSTM_Model_energy_node_48 = Sequential()
BiDirectonal_LSTM_Model_energy_node_48.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_energy_node_48.add(Dense(1))
BiDirectonal_LSTM_Model_energy_node_48.compile(loss='mean_squared_error',optimizer='adam')

BiDirectonal_LSTM_Model_pos_x_node_7.fit(X_training_data_reshaped_node_7,y_training_data_pos_x_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_pos_x_node_7),epochs=5,batch_size=10,verbose=1)
BiDirectonal_LSTM_Model_pos_y_node_7.fit(X_training_data_reshaped_node_7,y_training_data_pos_y_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_pos_y_node_7),epochs=5,batch_size=10,verbose=1)
BiDirectonal_LSTM_Model_speed_node_7.fit(X_training_data_reshaped_node_7,y_training_data_speed_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_speed_node_7),epochs=5,batch_size=10,verbose=1)
BiDirectonal_LSTM_Model_energy_node_7.fit(X_training_data_reshaped_node_7,y_training_data_energy_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_energy_node_7),epochs=5,batch_size=10,verbose=1)

BiDirectonal_LSTM_Model_pos_x_node_15.fit(X_training_data_reshaped_node_15,y_training_data_pos_x_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_pos_x_node_15),epochs=5,batch_size=10,verbose=1)
BiDirectonal_LSTM_Model_pos_y_node_15.fit(X_training_data_reshaped_node_15,y_training_data_pos_y_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_pos_y_node_15),epochs=5,batch_size=10,verbose=1)
BiDirectonal_LSTM_Model_speed_node_15.fit(X_training_data_reshaped_node_15,y_training_data_speed_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_speed_node_15),epochs=5,batch_size=10,verbose=1)
BiDirectonal_LSTM_Model_energy_node_15.fit(X_training_data_reshaped_node_15,y_training_data_energy_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_energy_node_15),epochs=5,batch_size=10,verbose=1)

BiDirectonal_LSTM_Model_pos_x_node_24.fit(X_training_data_reshaped_node_24,y_training_data_pos_x_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_pos_x_node_24),epochs=5,batch_size=10,verbose=1)
BiDirectonal_LSTM_Model_pos_y_node_24.fit(X_training_data_reshaped_node_24,y_training_data_pos_y_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_pos_y_node_24),epochs=5,batch_size=10,verbose=1)
BiDirectonal_LSTM_Model_speed_node_24.fit(X_training_data_reshaped_node_24,y_training_data_speed_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_speed_node_24),epochs=5,batch_size=10,verbose=1)
BiDirectonal_LSTM_Model_energy_node_24.fit(X_training_data_reshaped_node_24,y_training_data_energy_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_energy_node_24),epochs=5,batch_size=10,verbose=1)

BiDirectonal_LSTM_Model_pos_x_node_33.fit(X_training_data_reshaped_node_33,y_training_data_pos_x_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_pos_x_node_33),epochs=5,batch_size=10,verbose=1)
BiDirectonal_LSTM_Model_pos_y_node_33.fit(X_training_data_reshaped_node_33,y_training_data_pos_y_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_pos_y_node_33),epochs=5,batch_size=10,verbose=1)
BiDirectonal_LSTM_Model_speed_node_33.fit(X_training_data_reshaped_node_33,y_training_data_speed_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_speed_node_33),epochs=5,batch_size=10,verbose=1)
BiDirectonal_LSTM_Model_energy_node_33.fit(X_training_data_reshaped_node_33,y_training_data_energy_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_energy_node_33),epochs=5,batch_size=10,verbose=1)

BiDirectonal_LSTM_Model_pos_x_node_48.fit(X_training_data_reshaped_node_48,y_training_data_pos_x_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_pos_x_node_48),epochs=5,batch_size=10,verbose=1)
BiDirectonal_LSTM_Model_pos_y_node_48.fit(X_training_data_reshaped_node_48,y_training_data_pos_y_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_pos_y_node_48),epochs=5,batch_size=10,verbose=1)
BiDirectonal_LSTM_Model_speed_node_48.fit(X_training_data_reshaped_node_48,y_training_data_speed_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_speed_node_48),epochs=5,batch_size=10,verbose=1)
BiDirectonal_LSTM_Model_energy_node_48.fit(X_training_data_reshaped_node_48,y_training_data_energy_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_energy_node_48),epochs=5,batch_size=10,verbose=1)

Epoch 1/5
195/195 [==============================] - 4s 5ms/step - loss: 32189.6296 - val_loss: 469.9898
Epoch 2/5
195/195 [==============================] - ETA: 0s - loss: 557.565 - 1s 3ms/step - loss: 552.8971 - val_loss: 313.9742
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 449.4431 - val_loss: 281.5842
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 337.7806 - val_loss: 251.7953
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 318.0099 - val_loss: 239.4062
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 40112.5250 - val_loss: 4384.0352
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 6920.7124 - val_loss: 3910.5327
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 6629.5243 - val_loss: 4277.4990
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 6307.6049 - val_loss: 3935.1450
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 5409.2180 - val_loss: 4917.8135
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 11.9000 - val_loss: 5.1021
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 3.0683 - val_loss: 2.8765
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 1.5816 - val_loss: 2.0943
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 0.7018 - val_loss: 0.5179
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 0.3253 - val_loss: 0.4054
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 266416.5851 - val_loss: 64872.6953
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 26904.9105 - val_loss: 42946.5117
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 8766.6962 - val_loss: 41191.3906
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 7610.6842 - val_loss: 42584.5508
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 6642.3353 - val_loss: 38463.2500
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 53720.0008 - val_loss: 18081.2949
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 1276.6769 - val_loss: 25622.8457
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 1243.9814 - val_loss: 26542.1367
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 691.8695 - val_loss: 27055.8320
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 629.3897 - val_loss: 26859.2969
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 57638.3752 - val_loss: 12430.1924
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 1265.8402 - val_loss: 8997.6777
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 1023.1906 - val_loss: 9259.2354
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 850.7094 - val_loss: 7849.6304
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 916.2834 - val_loss: 7562.3745
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 6.3294 - val_loss: 2.2895
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 3.4733 - val_loss: 1.3414
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 1.4471 - val_loss: 2.3946
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 0.4245 - val_loss: 1.0357
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 0.1782 - val_loss: 0.6638
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 477103.2903 - val_loss: 94278.5703
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 29831.4582 - val_loss: 133241.3906
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 9696.3319 - val_loss: 186774.8438
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 8647.7514 - val_loss: 161329.3750
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 6751.6569 - val_loss: 169530.5625
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 95971.4912 - val_loss: 4351.5073
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 3265.7186 - val_loss: 3410.5774
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 1840.8763 - val_loss: 4212.0820
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 1194.8577 - val_loss: 3850.4102
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 918.9136 - val_loss: 5323.2515
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 20439.4449 - val_loss: 11809.9854
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 7996.5994 - val_loss: 8305.4443
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 5624.5941 - val_loss: 2760.4106
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 1982.2739 - val_loss: 554.0029
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 1120.0890 - val_loss: 639.4811
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 8.6530 - val_loss: 6.8291
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 1.4695 - val_loss: 6.1554
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 1.3409 - val_loss: 5.5991
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 1.0273 - val_loss: 1.9767
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 0.2442 - val_loss: 0.8534
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 2293880.5204 - val_loss: 355534.3438
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 16041.1125 - val_loss: 322084.2500
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 9211.9477 - val_loss: 303243.3750
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 8533.4503 - val_loss: 270037.0000
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 9947.2975 - val_loss: 267906.0938
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 76998.6234 - val_loss: 5967.6953
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 2743.2167 - val_loss: 5013.7778
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 1705.3069 - val_loss: 3641.4001
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 1519.7831 - val_loss: 4673.7603
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 1294.9473 - val_loss: 4264.8008
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 73489.7944 - val_loss: 13156.7529
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 6320.1391 - val_loss: 10870.6426
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 5320.2287 - val_loss: 10471.4121
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 5094.8946 - val_loss: 8641.1670
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 3214.8019 - val_loss: 5393.4380
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 7.3959 - val_loss: 3.2328
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 2.7597 - val_loss: 2.6193
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 1.6203 - val_loss: 1.2921
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 0.3349 - val_loss: 1.3616
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 0.2101 - val_loss: 2.2153
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 677816.3522 - val_loss: 304007.6250
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 18113.7515 - val_loss: 291531.7812
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 9665.7165 - val_loss: 310423.4375
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 9263.9380 - val_loss: 327575.3750
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 8415.5979 - val_loss: 296727.0312
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 132177.8099 - val_loss: 6545.3784
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 3428.1380 - val_loss: 5698.7998
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 885.1409 - val_loss: 3370.7212
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 182.9489 - val_loss: 2785.7986
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 57.2493 - val_loss: 3222.5007
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 20514.2372 - val_loss: 1192.2423
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 597.2907 - val_loss: 247.9480
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 134.9969 - val_loss: 122.9966
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 25.4889 - val_loss: 62.5902
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 8.5168 - val_loss: 58.2666
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 11.8330 - val_loss: 6.3638
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 4.4394 - val_loss: 6.2951
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 3.1755 - val_loss: 5.0679
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 0.3292 - val_loss: 3.2493
Epoch 5/5
195/195 [==============================] - 1s 3ms/step - loss: 0.1387 - val_loss: 2.1511
Epoch 1/5
195/195 [==============================] - 4s 6ms/step - loss: 3898263.0855 - val_loss: 2895052.5000
Epoch 2/5
195/195 [==============================] - 1s 3ms/step - loss: 68508.8347 - val_loss: 2383130.0000
Epoch 3/5
195/195 [==============================] - 1s 3ms/step - loss: 37124.5642 - val_loss: 2324319.5000
Epoch 4/5
195/195 [==============================] - 1s 3ms/step - loss: 21975.5433 - val_loss: 2182247.5000
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 20057.3396 - val_loss: 2228157.7500

<tensorflow.python.keras.callbacks.History at 0x195fcb2cca0>

train_predict_BiDirectonal_LSTM_Model_pos_x_node_7 = BiDirectonal_LSTM_Model_pos_x_node_7.predict(X_training_data_reshaped_node_7)
test_predict_BiDirectonal_LSTM_Model_pos_x_node_7 = BiDirectonal_LSTM_Model_pos_x_node_7.predict(X_testing_data_reshaped_node_7)
train_predict_BiDirectonal_LSTM_Model_pos_y_node_7 = BiDirectonal_LSTM_Model_pos_y_node_7.predict(X_training_data_reshaped_node_7)
test_predict_BiDirectonal_LSTM_Model_pos_y_node_7 = BiDirectonal_LSTM_Model_pos_y_node_7.predict(X_testing_data_reshaped_node_7)
train_predict_BiDirectonal_LSTM_Model_speed_node_7 = BiDirectonal_LSTM_Model_speed_node_7.predict(X_training_data_reshaped_node_7)
test_predict_BiDirectonal_LSTM_Model_speed_node_7 = BiDirectonal_LSTM_Model_speed_node_7.predict(X_testing_data_reshaped_node_7)
train_predict_BiDirectonal_LSTM_Model_energy_node_7 = BiDirectonal_LSTM_Model_energy_node_7.predict(X_training_data_reshaped_node_7)
test_predict_BiDirectonal_LSTM_Model_energy_node_7 = BiDirectonal_LSTM_Model_energy_node_7.predict(X_testing_data_reshaped_node_7)

train_predict_BiDirectonal_LSTM_Model_pos_x_node_15 = BiDirectonal_LSTM_Model_pos_x_node_15.predict(X_training_data_reshaped_node_15)
test_predict_BiDirectonal_LSTM_Model_pos_x_node_15 = BiDirectonal_LSTM_Model_pos_x_node_15.predict(X_testing_data_reshaped_node_15)
train_predict_BiDirectonal_LSTM_Model_pos_y_node_15 = BiDirectonal_LSTM_Model_pos_y_node_15.predict(X_training_data_reshaped_node_15)
test_predict_BiDirectonal_LSTM_Model_pos_y_node_15 = BiDirectonal_LSTM_Model_pos_y_node_15.predict(X_testing_data_reshaped_node_15)
train_predict_BiDirectonal_LSTM_Model_speed_node_15 = BiDirectonal_LSTM_Model_speed_node_15.predict(X_training_data_reshaped_node_15)
test_predict_BiDirectonal_LSTM_Model_speed_node_15 = BiDirectonal_LSTM_Model_speed_node_15.predict(X_testing_data_reshaped_node_15)
train_predict_BiDirectonal_LSTM_Model_energy_node_15 = BiDirectonal_LSTM_Model_energy_node_15.predict(X_training_data_reshaped_node_15)
test_predict_BiDirectonal_LSTM_Model_energy_node_15 = BiDirectonal_LSTM_Model_energy_node_15.predict(X_testing_data_reshaped_node_15)

train_predict_BiDirectonal_LSTM_Model_pos_x_node_24 = BiDirectonal_LSTM_Model_pos_x_node_24.predict(X_training_data_reshaped_node_24)
test_predict_BiDirectonal_LSTM_Model_pos_x_node_24 = BiDirectonal_LSTM_Model_pos_x_node_24.predict(X_testing_data_reshaped_node_24)
train_predict_BiDirectonal_LSTM_Model_pos_y_node_24 = BiDirectonal_LSTM_Model_pos_y_node_24.predict(X_training_data_reshaped_node_24)
test_predict_BiDirectonal_LSTM_Model_pos_y_node_24 = BiDirectonal_LSTM_Model_pos_y_node_24.predict(X_testing_data_reshaped_node_24)
train_predict_BiDirectonal_LSTM_Model_speed_node_24 = BiDirectonal_LSTM_Model_speed_node_24.predict(X_training_data_reshaped_node_24)
test_predict_BiDirectonal_LSTM_Model_speed_node_24 = BiDirectonal_LSTM_Model_speed_node_24.predict(X_testing_data_reshaped_node_24)
train_predict_BiDirectonal_LSTM_Model_energy_node_24 = BiDirectonal_LSTM_Model_energy_node_24.predict(X_training_data_reshaped_node_24)
test_predict_BiDirectonal_LSTM_Model_energy_node_24 = BiDirectonal_LSTM_Model_energy_node_24.predict(X_testing_data_reshaped_node_24)

train_predict_BiDirectonal_LSTM_Model_pos_x_node_33 = BiDirectonal_LSTM_Model_pos_x_node_33.predict(X_training_data_reshaped_node_33)
test_predict_BiDirectonal_LSTM_Model_pos_x_node_33 = BiDirectonal_LSTM_Model_pos_x_node_33.predict(X_testing_data_reshaped_node_33)
train_predict_BiDirectonal_LSTM_Model_pos_y_node_33 = BiDirectonal_LSTM_Model_pos_y_node_33.predict(X_training_data_reshaped_node_33)
test_predict_BiDirectonal_LSTM_Model_pos_y_node_33 = BiDirectonal_LSTM_Model_pos_y_node_33.predict(X_testing_data_reshaped_node_33)
train_predict_BiDirectonal_LSTM_Model_speed_node_33 = BiDirectonal_LSTM_Model_speed_node_33.predict(X_training_data_reshaped_node_33)
test_predict_BiDirectonal_LSTM_Model_speed_node_33 = BiDirectonal_LSTM_Model_speed_node_33.predict(X_testing_data_reshaped_node_33)
train_predict_BiDirectonal_LSTM_Model_energy_node_33 = BiDirectonal_LSTM_Model_energy_node_33.predict(X_training_data_reshaped_node_33)
test_predict_BiDirectonal_LSTM_Model_energy_node_33 = BiDirectonal_LSTM_Model_energy_node_33.predict(X_testing_data_reshaped_node_33)

train_predict_BiDirectonal_LSTM_Model_pos_x_node_48 = BiDirectonal_LSTM_Model_pos_x_node_48.predict(X_training_data_reshaped_node_48)
test_predict_BiDirectonal_LSTM_Model_pos_x_node_48 = BiDirectonal_LSTM_Model_pos_x_node_48.predict(X_testing_data_reshaped_node_48)
train_predict_BiDirectonal_LSTM_Model_pos_y_node_48 = BiDirectonal_LSTM_Model_pos_y_node_48.predict(X_training_data_reshaped_node_48)
test_predict_BiDirectonal_LSTM_Model_pos_y_node_48 = BiDirectonal_LSTM_Model_pos_y_node_48.predict(X_testing_data_reshaped_node_48)
train_predict_BiDirectonal_LSTM_Model_speed_node_48 = BiDirectonal_LSTM_Model_speed_node_48.predict(X_training_data_reshaped_node_48)
test_predict_BiDirectonal_LSTM_Model_speed_node_48 = BiDirectonal_LSTM_Model_speed_node_48.predict(X_testing_data_reshaped_node_48)
train_predict_BiDirectonal_LSTM_Model_energy_node_48 = BiDirectonal_LSTM_Model_energy_node_48.predict(X_training_data_reshaped_node_48)
test_predict_BiDirectonal_LSTM_Model_energy_node_48 = BiDirectonal_LSTM_Model_energy_node_48.predict(X_testing_data_reshaped_node_48)

RMSE

print("\n\nRMSE on Training Data by Bi-Directional LSTM: ")
print("==============================================\n\n")

print("\n\nRMSE of Node 7: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_7,train_predict_BiDirectonal_LSTM_Model_pos_x_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_7,train_predict_BiDirectonal_LSTM_Model_pos_y_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_7,train_predict_BiDirectonal_LSTM_Model_speed_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_7,train_predict_BiDirectonal_LSTM_Model_energy_node_7)))
      
print("\n\nRMSE of Node 15: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_15,train_predict_BiDirectonal_LSTM_Model_pos_x_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_15,train_predict_BiDirectonal_LSTM_Model_pos_y_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_15,train_predict_BiDirectonal_LSTM_Model_speed_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_15,train_predict_BiDirectonal_LSTM_Model_energy_node_15)))
      
print("\n\nRMSE of Node 24: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_24,train_predict_BiDirectonal_LSTM_Model_pos_x_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_24,train_predict_BiDirectonal_LSTM_Model_pos_y_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_24,train_predict_BiDirectonal_LSTM_Model_speed_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_24,train_predict_BiDirectonal_LSTM_Model_energy_node_24)))

print("\n\nRMSE of Node 33: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_33,train_predict_BiDirectonal_LSTM_Model_pos_x_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_33,train_predict_BiDirectonal_LSTM_Model_pos_y_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_33,train_predict_BiDirectonal_LSTM_Model_speed_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_33,train_predict_BiDirectonal_LSTM_Model_energy_node_33)))
      
print("\n\nRMSE of Node 48: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_48,train_predict_BiDirectonal_LSTM_Model_pos_x_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_48,train_predict_BiDirectonal_LSTM_Model_pos_y_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_48,train_predict_BiDirectonal_LSTM_Model_speed_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_48,train_predict_BiDirectonal_LSTM_Model_energy_node_48)))

print("\n\nRMSE on Testing Data by Bi-Directional LSTM: ")
print("=============================================\n\n")
      
print("\n\nRMSE of Node 7: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_BiDirectonal_LSTM_Model_pos_x_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_BiDirectonal_LSTM_Model_pos_y_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_BiDirectonal_LSTM_Model_speed_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_BiDirectonal_LSTM_Model_energy_node_7)))
      
print("\n\nRMSE of Node 15: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_BiDirectonal_LSTM_Model_pos_x_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_BiDirectonal_LSTM_Model_pos_y_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_BiDirectonal_LSTM_Model_speed_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_BiDirectonal_LSTM_Model_energy_node_15)))
     
print("\n\nRMSE of Node 24: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_BiDirectonal_LSTM_Model_pos_x_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_24,test_predict_BiDirectonal_LSTM_Model_pos_y_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_BiDirectonal_LSTM_Model_speed_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_BiDirectonal_LSTM_Model_energy_node_24)))
      
print("\n\nRMSE of Node 33: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_BiDirectonal_LSTM_Model_pos_x_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_BiDirectonal_LSTM_Model_pos_y_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_BiDirectonal_LSTM_Model_speed_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_BiDirectonal_LSTM_Model_energy_node_33)))
      
print("\n\nRMSE of Node 48: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_BiDirectonal_LSTM_Model_pos_x_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_BiDirectonal_LSTM_Model_pos_y_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_BiDirectonal_LSTM_Model_speed_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_BiDirectonal_LSTM_Model_energy_node_48)))

RMSE on Training Data by Bi-Directional LSTM: 
==============================================




RMSE of Node 7: 
======================================


18.42230735272556
66.19180528916202
0.5671668681639104
77.13827806454167


RMSE of Node 15: 
======================================


24.304127003436246
29.14492006221184
0.42802572232609387
81.7756680476229


RMSE of Node 24: 
======================================


29.697526911048534
32.0464558839694
0.39748939557370205
89.69518114509812


RMSE of Node 33: 
======================================


32.89917103360774
37.17053485662294
0.6010035323543809
86.6826415738472


RMSE of Node 48: 
======================================


8.17105187022975
1.9643553451051685
0.33309919277040334
137.38962657177902


RMSE on Testing Data by Bi-Directional LSTM: 
=============================================




RMSE of Node 7: 
======================================


15.472769223108413
70.12713281868652
0.6367309253112398
196.12055188917748


RMSE of Node 15: 
======================================


163.88808119833243
86.96190672294681
0.8147339061807343
411.74089137786603


RMSE of Node 24: 
======================================


72.9606199636792
25.28796170794887
0.9237705686606663
517.5964521813826


RMSE of Node 33: 
======================================


65.30544743297659
73.44002737925149
1.4883888771416753
544.7265719091582


RMSE of Node 48: 
======================================


56.767080844719466
7.633256587911894
1.46665031821823
1492.7014867622406

Graph

print("\n\nGraph of Node 7: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_7)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_x_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_7)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_y_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_7)
plt.plot(test_predict_BiDirectonal_LSTM_Model_speed_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_7)
plt.plot(test_predict_BiDirectonal_LSTM_Model_energy_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 15: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_15)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_x_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_15)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_y_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_15)
plt.plot(test_predict_BiDirectonal_LSTM_Model_speed_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_15)
plt.plot(test_predict_BiDirectonal_LSTM_Model_energy_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 24: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_24)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_x_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_24)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_y_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_24)
plt.plot(test_predict_BiDirectonal_LSTM_Model_speed_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_24)
plt.plot(test_predict_BiDirectonal_LSTM_Model_energy_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 33: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_33)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_x_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_33)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_y_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_33)
plt.plot(test_predict_BiDirectonal_LSTM_Model_speed_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_33)
plt.plot(test_predict_BiDirectonal_LSTM_Model_energy_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 48: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_48)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_x_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_48)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_y_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_48)
plt.plot(test_predict_BiDirectonal_LSTM_Model_speed_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_48)
plt.plot(test_predict_BiDirectonal_LSTM_Model_energy_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

Graph of Node 7: 
======================================

Graph of Node 15: 
======================================

Graph of Node 24: 
======================================

Graph of Node 33: 
======================================

Graph of Node 48: 
======================================

====================

GRU

====================

GRU_Model_pos_x_node_7 = Sequential()
GRU_Model_pos_x_node_7.add(GRU(50,input_shape=(4,1)))
GRU_Model_pos_x_node_7.add(Dense(1000))
GRU_Model_pos_x_node_7.add(Dense(1))
GRU_Model_pos_x_node_7.compile(loss='mean_squared_error',optimizer='adam')
GRU_Model_pos_y_node_7 = Sequential()
GRU_Model_pos_y_node_7.add(GRU(50,input_shape=(4,1)))
GRU_Model_pos_y_node_7.add(Dense(1000))
GRU_Model_pos_y_node_7.add(Dense(1))
GRU_Model_pos_y_node_7.compile(loss='mean_squared_error',optimizer='adam')
GRU_Model_speed_node_7 = Sequential()
GRU_Model_speed_node_7.add(GRU(50,input_shape=(4,1)))
GRU_Model_speed_node_7.add(Dense(1000))
GRU_Model_speed_node_7.add(Dense(1))
GRU_Model_speed_node_7.compile(loss='mean_squared_error',optimizer='adam')
GRU_Model_energy_node_7 = Sequential()
GRU_Model_energy_node_7.add(GRU(50,input_shape=(4,1)))
GRU_Model_energy_node_7.add(Dense(1000))
GRU_Model_energy_node_7.add(Dense(1))
GRU_Model_energy_node_7.compile(loss='mean_squared_error',optimizer='adam')

GRU_Model_pos_x_node_15 = Sequential()
GRU_Model_pos_x_node_15.add(GRU(50,input_shape=(4,1)))
GRU_Model_pos_x_node_15.add(Dense(1000))
GRU_Model_pos_x_node_15.add(Dense(1))
GRU_Model_pos_x_node_15.compile(loss='mean_squared_error',optimizer='adam')
GRU_Model_pos_y_node_15 = Sequential()
GRU_Model_pos_y_node_15.add(GRU(50,input_shape=(4,1)))
GRU_Model_pos_y_node_15.add(Dense(1000))
GRU_Model_pos_y_node_15.add(Dense(1))
GRU_Model_pos_y_node_15.compile(loss='mean_squared_error',optimizer='adam')
GRU_Model_speed_node_15 = Sequential()
GRU_Model_speed_node_15.add(GRU(50,input_shape=(4,1)))
GRU_Model_speed_node_15.add(Dense(1000))
GRU_Model_speed_node_15.add(Dense(1))
GRU_Model_speed_node_15.compile(loss='mean_squared_error',optimizer='adam')
GRU_Model_energy_node_15 = Sequential()
GRU_Model_energy_node_15.add(GRU(50,input_shape=(4,1)))
GRU_Model_energy_node_15.add(Dense(1000))
GRU_Model_energy_node_15.add(Dense(1))
GRU_Model_energy_node_15.compile(loss='mean_squared_error',optimizer='adam')

GRU_Model_pos_x_node_24 = Sequential()
GRU_Model_pos_x_node_24.add(GRU(50,input_shape=(4,1)))
GRU_Model_pos_x_node_24.add(Dense(1000))
GRU_Model_pos_x_node_24.add(Dense(1))
GRU_Model_pos_x_node_24.compile(loss='mean_squared_error',optimizer='adam')
GRU_Model_pos_y_node_24 = Sequential()
GRU_Model_pos_y_node_24.add(GRU(50,input_shape=(4,1)))
GRU_Model_pos_y_node_24.add(Dense(1000))
GRU_Model_pos_y_node_24.add(Dense(1))
GRU_Model_pos_y_node_24.compile(loss='mean_squared_error',optimizer='adam')
GRU_Model_speed_node_24 = Sequential()
GRU_Model_speed_node_24.add(GRU(50,input_shape=(4,1)))
GRU_Model_speed_node_24.add(Dense(1000))
GRU_Model_speed_node_24.add(Dense(1))
GRU_Model_speed_node_24.compile(loss='mean_squared_error',optimizer='adam')
GRU_Model_energy_node_24 = Sequential()
GRU_Model_energy_node_24.add(GRU(50,input_shape=(4,1)))
GRU_Model_energy_node_24.add(Dense(1000))
GRU_Model_energy_node_24.add(Dense(1))
GRU_Model_energy_node_24.compile(loss='mean_squared_error',optimizer='adam')

GRU_Model_pos_x_node_33 = Sequential()
GRU_Model_pos_x_node_33.add(GRU(50,input_shape=(4,1)))
GRU_Model_pos_x_node_33.add(Dense(1000))
GRU_Model_pos_x_node_33.add(Dense(1))
GRU_Model_pos_x_node_33.compile(loss='mean_squared_error',optimizer='adam')
GRU_Model_pos_y_node_33 = Sequential()
GRU_Model_pos_y_node_33.add(GRU(50,input_shape=(4,1)))
GRU_Model_pos_y_node_33.add(Dense(1000))
GRU_Model_pos_y_node_33.add(Dense(1))
GRU_Model_pos_y_node_33.compile(loss='mean_squared_error',optimizer='adam')
GRU_Model_speed_node_33 = Sequential()
GRU_Model_speed_node_33.add(GRU(50,input_shape=(4,1)))
GRU_Model_speed_node_33.add(Dense(1000))
GRU_Model_speed_node_33.add(Dense(1))
GRU_Model_speed_node_33.compile(loss='mean_squared_error',optimizer='adam')
GRU_Model_energy_node_33 = Sequential()
GRU_Model_energy_node_33.add(GRU(50,input_shape=(4,1)))
GRU_Model_energy_node_33.add(Dense(1000))
GRU_Model_energy_node_33.add(Dense(1))
GRU_Model_energy_node_33.compile(loss='mean_squared_error',optimizer='adam')

GRU_Model_pos_x_node_48 = Sequential()
GRU_Model_pos_x_node_48.add(GRU(50,input_shape=(4,1)))
GRU_Model_pos_x_node_48.add(Dense(1000))
GRU_Model_pos_x_node_48.add(Dense(1))
GRU_Model_pos_x_node_48.compile(loss='mean_squared_error',optimizer='adam')
GRU_Model_pos_y_node_48 = Sequential()
GRU_Model_pos_y_node_48.add(GRU(50,input_shape=(4,1)))
GRU_Model_pos_y_node_48.add(Dense(1000))
GRU_Model_pos_y_node_48.add(Dense(1))
GRU_Model_pos_y_node_48.compile(loss='mean_squared_error',optimizer='adam')
GRU_Model_speed_node_48 = Sequential()
GRU_Model_speed_node_48.add(GRU(50,input_shape=(4,1)))
GRU_Model_speed_node_48.add(Dense(1000))
GRU_Model_speed_node_48.add(Dense(1))
GRU_Model_speed_node_48.compile(loss='mean_squared_error',optimizer='adam')
GRU_Model_energy_node_48 = Sequential()
GRU_Model_energy_node_48.add(GRU(50,input_shape=(4,1)))
GRU_Model_energy_node_48.add(Dense(1000))
GRU_Model_energy_node_48.add(Dense(1))
GRU_Model_energy_node_48.compile(loss='mean_squared_error',optimizer='adam')

GRU_Model_pos_x_node_7.fit(X_training_data_reshaped_node_7,y_training_data_pos_x_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_pos_x_node_7),epochs=5,batch_size=10,verbose=1)
GRU_Model_pos_y_node_7.fit(X_training_data_reshaped_node_7,y_training_data_pos_y_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_pos_y_node_7),epochs=5,batch_size=10,verbose=1)
GRU_Model_speed_node_7.fit(X_training_data_reshaped_node_7,y_training_data_speed_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_speed_node_7),epochs=5,batch_size=10,verbose=1)
GRU_Model_energy_node_7.fit(X_training_data_reshaped_node_7,y_training_data_energy_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_energy_node_7),epochs=5,batch_size=10,verbose=1)

GRU_Model_pos_x_node_15.fit(X_training_data_reshaped_node_15,y_training_data_pos_x_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_pos_x_node_15),epochs=5,batch_size=10,verbose=1)
GRU_Model_pos_y_node_15.fit(X_training_data_reshaped_node_15,y_training_data_pos_y_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_pos_y_node_15),epochs=5,batch_size=10,verbose=1)
GRU_Model_speed_node_15.fit(X_training_data_reshaped_node_15,y_training_data_speed_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_speed_node_15),epochs=5,batch_size=10,verbose=1)
GRU_Model_energy_node_15.fit(X_training_data_reshaped_node_15,y_training_data_energy_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_energy_node_15),epochs=5,batch_size=10,verbose=1)

GRU_Model_pos_x_node_24.fit(X_training_data_reshaped_node_24,y_training_data_pos_x_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_pos_x_node_24),epochs=5,batch_size=10,verbose=1)
GRU_Model_pos_y_node_24.fit(X_training_data_reshaped_node_24,y_training_data_pos_y_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_pos_y_node_24),epochs=5,batch_size=10,verbose=1)
GRU_Model_speed_node_24.fit(X_training_data_reshaped_node_24,y_training_data_speed_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_speed_node_24),epochs=5,batch_size=10,verbose=1)
GRU_Model_energy_node_24.fit(X_training_data_reshaped_node_24,y_training_data_energy_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_energy_node_24),epochs=5,batch_size=10,verbose=1)

GRU_Model_pos_x_node_33.fit(X_training_data_reshaped_node_33,y_training_data_pos_x_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_pos_x_node_33),epochs=5,batch_size=10,verbose=1)
GRU_Model_pos_y_node_33.fit(X_training_data_reshaped_node_33,y_training_data_pos_y_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_pos_y_node_33),epochs=5,batch_size=10,verbose=1)
GRU_Model_speed_node_33.fit(X_training_data_reshaped_node_33,y_training_data_speed_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_speed_node_33),epochs=5,batch_size=10,verbose=1)
GRU_Model_energy_node_33.fit(X_training_data_reshaped_node_33,y_training_data_energy_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_energy_node_33),epochs=5,batch_size=10,verbose=1)

GRU_Model_pos_x_node_48.fit(X_training_data_reshaped_node_48,y_training_data_pos_x_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_pos_x_node_48),epochs=5,batch_size=10,verbose=1)
GRU_Model_pos_y_node_48.fit(X_training_data_reshaped_node_48,y_training_data_pos_y_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_pos_y_node_48),epochs=5,batch_size=10,verbose=1)
GRU_Model_speed_node_48.fit(X_training_data_reshaped_node_48,y_training_data_speed_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_speed_node_48),epochs=5,batch_size=10,verbose=1)
GRU_Model_energy_node_48.fit(X_training_data_reshaped_node_48,y_training_data_energy_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_energy_node_48),epochs=5,batch_size=10,verbose=1)

Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 19877.9371 - val_loss: 1837.2119
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 983.5955 - val_loss: 1283.8242
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 565.8454 - val_loss: 1190.0034
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 528.9743 - val_loss: 983.0772
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 471.1116 - val_loss: 724.2157
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 28255.1364 - val_loss: 2989.7141
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 5683.5460 - val_loss: 4049.0979
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 4999.4161 - val_loss: 5171.1016
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 4470.0973 - val_loss: 6173.8022
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 3893.5176 - val_loss: 6295.1343
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 5.4306 - val_loss: 1.6480
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 0.9158 - val_loss: 0.3768
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 0.2513 - val_loss: 0.2862
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 0.2835 - val_loss: 0.2795
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 0.4061 - val_loss: 0.2358
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 213562.3599 - val_loss: 113951.4922
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 107157.5694 - val_loss: 95130.1250
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 47299.1129 - val_loss: 27384.4648
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 1756.7445 - val_loss: 28444.0605
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 245.1841 - val_loss: 28401.6230
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 34595.4792 - val_loss: 12206.5400
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 1793.2031 - val_loss: 19510.2695
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 1111.6358 - val_loss: 19779.5449
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 598.8955 - val_loss: 21726.3477
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 426.8194 - val_loss: 19477.3887
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 35046.0746 - val_loss: 4328.2344
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 1434.7695 - val_loss: 6233.1450
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 1334.0415 - val_loss: 4529.0352
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 1319.1557 - val_loss: 3150.0276
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 1288.4363 - val_loss: 5345.1411
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 3.8926 - val_loss: 0.5587
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 0.2305 - val_loss: 0.4072
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 0.1630 - val_loss: 0.5024
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 0.0928 - val_loss: 0.8913
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 0.2050 - val_loss: 0.6176
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 396932.9429 - val_loss: 211447.1406
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 245236.6373 - val_loss: 90186.4609
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 101659.5253 - val_loss: 58915.1992
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 4183.9713 - val_loss: 63612.9844
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 1110.8375 - val_loss: 65404.6211
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 59430.8857 - val_loss: 5945.0918
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 5766.1787 - val_loss: 2955.5972
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 997.0505 - val_loss: 1973.4316
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 761.9979 - val_loss: 1629.1990
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 736.0356 - val_loss: 1936.1908
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 14712.3095 - val_loss: 8956.8701
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 6331.2420 - val_loss: 8259.3389
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 6195.4831 - val_loss: 7844.1924
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 6022.9997 - val_loss: 7497.3477
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 5900.3000 - val_loss: 7289.8896
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 3.2596 - val_loss: 5.1522
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 0.4039 - val_loss: 0.7103
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 0.1245 - val_loss: 0.6676
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 0.1844 - val_loss: 0.7868
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 0.0865 - val_loss: 0.8522
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 1770166.5261 - val_loss: 720548.8125
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 220650.9756 - val_loss: 634893.9375
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 128517.8780 - val_loss: 686787.8750
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 92240.8389 - val_loss: 609857.6875
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 83424.8713 - val_loss: 461474.8750
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 49141.7810 - val_loss: 7476.6470
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 5888.8011 - val_loss: 4513.1475
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 3638.7358 - val_loss: 5961.7559
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 2544.8954 - val_loss: 4053.7666
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 1805.1947 - val_loss: 4206.4561
Epoch 1/5
195/195 [==============================] - 4s 8ms/step - loss: 42278.0854 - val_loss: 7948.4951
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 5692.0866 - val_loss: 7974.1504
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 5322.2598 - val_loss: 7819.4014
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 5113.6369 - val_loss: 7743.3369
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 4942.6673 - val_loss: 8413.6777
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 4.3856 - val_loss: 2.0396
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 0.4395 - val_loss: 0.9546
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 0.1797 - val_loss: 0.8512
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 0.2200 - val_loss: 0.8135
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 0.1906 - val_loss: 0.7097
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 489211.8720 - val_loss: 235953.0625
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 102014.5839 - val_loss: 203124.5312
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 100072.0988 - val_loss: 203967.5938
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 70989.1667 - val_loss: 252478.7500
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 32109.2247 - val_loss: 219006.1250
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 86128.5894 - val_loss: 992.1761
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 174.4638 - val_loss: 1735.5767
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 105.8385 - val_loss: 2128.0281
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 92.8593 - val_loss: 2091.8425
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 100.3685 - val_loss: 2471.6455
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 11655.6587 - val_loss: 339.1677
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 48.6838 - val_loss: 100.5956
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 8.7239 - val_loss: 67.0432
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 2.8673 - val_loss: 48.2163
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 1.9172 - val_loss: 41.9425
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 6.4760 - val_loss: 3.2886
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 0.2045 - val_loss: 2.2315
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 0.1245 - val_loss: 2.5533
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 0.0837 - val_loss: 2.5310
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 0.0672 - val_loss: 2.2326
Epoch 1/5
195/195 [==============================] - 4s 7ms/step - loss: 3149215.3399 - val_loss: 1659367.6250
Epoch 2/5
195/195 [==============================] - 1s 4ms/step - loss: 519242.2643 - val_loss: 1620145.0000
Epoch 3/5
195/195 [==============================] - 1s 4ms/step - loss: 517820.5872 - val_loss: 1717804.6250
Epoch 4/5
195/195 [==============================] - 1s 4ms/step - loss: 511957.2411 - val_loss: 1664072.0000
Epoch 5/5
195/195 [==============================] - 1s 4ms/step - loss: 452628.5938 - val_loss: 1848406.5000

<tensorflow.python.keras.callbacks.History at 0x1964d69c760>

train_predict_GRU_Model_pos_x_node_7 = GRU_Model_pos_x_node_7.predict(X_training_data_reshaped_node_7)
test_predict_GRU_Model_pos_x_node_7 = GRU_Model_pos_x_node_7.predict(X_testing_data_reshaped_node_7)
train_predict_GRU_Model_pos_y_node_7 = GRU_Model_pos_y_node_7.predict(X_training_data_reshaped_node_7)
test_predict_GRU_Model_pos_y_node_7 = GRU_Model_pos_y_node_7.predict(X_testing_data_reshaped_node_7)
train_predict_GRU_Model_speed_node_7 = GRU_Model_speed_node_7.predict(X_training_data_reshaped_node_7)
test_predict_GRU_Model_speed_node_7 = GRU_Model_speed_node_7.predict(X_testing_data_reshaped_node_7)
train_predict_GRU_Model_energy_node_7 = GRU_Model_energy_node_7.predict(X_training_data_reshaped_node_7)
test_predict_GRU_Model_energy_node_7 = GRU_Model_energy_node_7.predict(X_testing_data_reshaped_node_7)

train_predict_GRU_Model_pos_x_node_15 = GRU_Model_pos_x_node_15.predict(X_training_data_reshaped_node_15)
test_predict_GRU_Model_pos_x_node_15 = GRU_Model_pos_x_node_15.predict(X_testing_data_reshaped_node_15)
train_predict_GRU_Model_pos_y_node_15 = GRU_Model_pos_y_node_15.predict(X_training_data_reshaped_node_15)
test_predict_GRU_Model_pos_y_node_15 = GRU_Model_pos_y_node_15.predict(X_testing_data_reshaped_node_15)
train_predict_GRU_Model_speed_node_15 = GRU_Model_speed_node_15.predict(X_training_data_reshaped_node_15)
test_predict_GRU_Model_speed_node_15 = GRU_Model_speed_node_15.predict(X_testing_data_reshaped_node_15)
train_predict_GRU_Model_energy_node_15 = GRU_Model_energy_node_15.predict(X_training_data_reshaped_node_15)
test_predict_GRU_Model_energy_node_15 = GRU_Model_energy_node_15.predict(X_testing_data_reshaped_node_15)

train_predict_GRU_Model_pos_x_node_24 = GRU_Model_pos_x_node_24.predict(X_training_data_reshaped_node_24)
test_predict_GRU_Model_pos_x_node_24 = GRU_Model_pos_x_node_24.predict(X_testing_data_reshaped_node_24)
train_predict_GRU_Model_pos_y_node_24 = GRU_Model_pos_y_node_24.predict(X_training_data_reshaped_node_24)
test_predict_GRU_Model_pos_y_node_24 = GRU_Model_pos_y_node_24.predict(X_testing_data_reshaped_node_24)
train_predict_GRU_Model_speed_node_24 = GRU_Model_speed_node_24.predict(X_training_data_reshaped_node_24)
test_predict_GRU_Model_speed_node_24 = GRU_Model_speed_node_24.predict(X_testing_data_reshaped_node_24)
train_predict_GRU_Model_energy_node_24 = GRU_Model_energy_node_24.predict(X_training_data_reshaped_node_24)
test_predict_GRU_Model_energy_node_24 = GRU_Model_energy_node_24.predict(X_testing_data_reshaped_node_24)

train_predict_GRU_Model_pos_x_node_33 = GRU_Model_pos_x_node_33.predict(X_training_data_reshaped_node_33)
test_predict_GRU_Model_pos_x_node_33 = GRU_Model_pos_x_node_33.predict(X_testing_data_reshaped_node_33)
train_predict_GRU_Model_pos_y_node_33 = GRU_Model_pos_y_node_33.predict(X_training_data_reshaped_node_33)
test_predict_GRU_Model_pos_y_node_33 = GRU_Model_pos_y_node_33.predict(X_testing_data_reshaped_node_33)
train_predict_GRU_Model_speed_node_33 = GRU_Model_speed_node_33.predict(X_training_data_reshaped_node_33)
test_predict_GRU_Model_speed_node_33 = GRU_Model_speed_node_33.predict(X_testing_data_reshaped_node_33)
train_predict_GRU_Model_energy_node_33 = GRU_Model_energy_node_33.predict(X_training_data_reshaped_node_33)
test_predict_GRU_Model_energy_node_33 = GRU_Model_energy_node_33.predict(X_testing_data_reshaped_node_33)

train_predict_GRU_Model_pos_x_node_48 = GRU_Model_pos_x_node_48.predict(X_training_data_reshaped_node_48)
test_predict_GRU_Model_pos_x_node_48 = GRU_Model_pos_x_node_48.predict(X_testing_data_reshaped_node_48)
train_predict_GRU_Model_pos_y_node_48 = GRU_Model_pos_y_node_48.predict(X_training_data_reshaped_node_48)
test_predict_GRU_Model_pos_y_node_48 = GRU_Model_pos_y_node_48.predict(X_testing_data_reshaped_node_48)
train_predict_GRU_Model_speed_node_48 = GRU_Model_speed_node_48.predict(X_training_data_reshaped_node_48)
test_predict_GRU_Model_speed_node_48 = GRU_Model_speed_node_48.predict(X_testing_data_reshaped_node_48)
train_predict_GRU_Model_energy_node_48 = GRU_Model_energy_node_48.predict(X_training_data_reshaped_node_48)
test_predict_GRU_Model_energy_node_48 = GRU_Model_energy_node_48.predict(X_testing_data_reshaped_node_48)

RMSE

print("\n\nRMSE on Training Data by GRU: ")
print("======================================\n\n")

print("\n\nRMSE of Node 7: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_7,train_predict_GRU_Model_pos_x_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_7,train_predict_GRU_Model_pos_y_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_7,train_predict_GRU_Model_speed_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_7,train_predict_GRU_Model_energy_node_7)))
      
print("\n\nRMSE of Node 15: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_15,train_predict_GRU_Model_pos_x_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_15,train_predict_GRU_Model_pos_y_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_15,train_predict_GRU_Model_speed_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_15,train_predict_GRU_Model_energy_node_15)))
      
print("\n\nRMSE of Node 24: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_24,train_predict_GRU_Model_pos_x_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_24,train_predict_GRU_Model_pos_y_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_24,train_predict_GRU_Model_speed_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_24,train_predict_GRU_Model_energy_node_24)))

print("\n\nRMSE of Node 33: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_33,train_predict_GRU_Model_pos_x_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_33,train_predict_GRU_Model_pos_y_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_33,train_predict_GRU_Model_speed_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_33,train_predict_GRU_Model_energy_node_33)))
      
print("\n\nRMSE of Node 48: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_48,train_predict_GRU_Model_pos_x_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_48,train_predict_GRU_Model_pos_y_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_48,train_predict_GRU_Model_speed_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_48,train_predict_GRU_Model_energy_node_48)))

print("\n\nRMSE on Testing Data by GRU: ")
print("=====================================\n\n")
      
print("\n\nRMSE of Node 7: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_GRU_Model_pos_x_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_GRU_Model_pos_y_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_GRU_Model_speed_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_GRU_Model_energy_node_7)))
      
print("\n\nRMSE of Node 15: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_GRU_Model_pos_x_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_GRU_Model_pos_y_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_GRU_Model_speed_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_GRU_Model_energy_node_15)))
     
print("\n\nRMSE of Node 24: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_GRU_Model_pos_x_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_24,test_predict_GRU_Model_pos_y_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_GRU_Model_speed_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_GRU_Model_energy_node_24)))
      
print("\n\nRMSE of Node 33: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_GRU_Model_pos_x_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_GRU_Model_pos_y_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_GRU_Model_speed_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_GRU_Model_energy_node_33)))
      
print("\n\nRMSE of Node 48: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_GRU_Model_pos_x_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_GRU_Model_pos_y_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_GRU_Model_speed_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_GRU_Model_energy_node_48)))

RMSE on Training Data by GRU: 
======================================




RMSE of Node 7: 
======================================


16.996573492867658
54.8341511625619
0.5052075422752197
23.59512800321984


RMSE of Node 15: 
======================================


20.657066435559383
34.79081257237088
0.39957579390837755
38.80626058010534


RMSE of Node 24: 
======================================


22.659284725758326
74.42649867404641
0.36668950366939523
246.34578126823115


RMSE of Node 33: 
======================================


37.013649640878974
70.04476321906223
0.3817785860805037
100.75893795297313


RMSE of Node 48: 
======================================


9.994468324767526
1.2309565254959485
0.28963635401627746
571.746346938228


RMSE on Testing Data by GRU: 
=====================================




RMSE of Node 7: 
======================================


26.911247497909503
79.34188876221245
0.485575171241919
168.52778792856125


RMSE of Node 15: 
======================================


139.56143742628595
73.11046521732577
0.7858934747961992
255.74325590863873


RMSE of Node 24: 
======================================


44.00216484194272
85.3808500780627
0.9231312058580767
679.3194368512528


RMSE of Node 33: 
======================================


64.85719612818674
91.72610847149676
0.8424116788231122
467.98088347075924


RMSE of Node 48: 
======================================


49.715648127865926
6.476301148672023
1.4941851685138519
1359.5611330777754

Graph

print("\n\nGraph of Node 7: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_7)
plt.plot(test_predict_GRU_Model_pos_x_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_7)
plt.plot(test_predict_GRU_Model_pos_y_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_7)
plt.plot(test_predict_GRU_Model_speed_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_7)
plt.plot(test_predict_GRU_Model_energy_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 15: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_15)
plt.plot(test_predict_GRU_Model_pos_x_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_15)
plt.plot(test_predict_GRU_Model_pos_y_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_15)
plt.plot(test_predict_GRU_Model_speed_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_15)
plt.plot(test_predict_GRU_Model_energy_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 24: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_24)
plt.plot(test_predict_GRU_Model_pos_x_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_24)
plt.plot(test_predict_GRU_Model_pos_y_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_24)
plt.plot(test_predict_GRU_Model_speed_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_24)
plt.plot(test_predict_GRU_Model_energy_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 33: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_33)
plt.plot(test_predict_GRU_Model_pos_x_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_33)
plt.plot(test_predict_GRU_Model_pos_y_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_33)
plt.plot(test_predict_GRU_Model_speed_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_33)
plt.plot(test_predict_GRU_Model_energy_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 48: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_48)
plt.plot(test_predict_GRU_Model_pos_x_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_48)
plt.plot(test_predict_GRU_Model_pos_y_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_48)
plt.plot(test_predict_GRU_Model_speed_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_48)
plt.plot(test_predict_GRU_Model_energy_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

Graph of Node 7: 
======================================

Graph of Node 15: 
======================================

Graph of Node 24: 
======================================

Graph of Node 33: 
======================================

Graph of Node 48: 
======================================

====================

RNN

====================

RNN_Model_pos_x_node_7 = Sequential()
RNN_Model_pos_x_node_7.add(RNN(50,input_shape=(4,1)))
RNN_Model_pos_x_node_7.add(Dense(1))
RNN_Model_pos_x_node_7.compile(loss='mean_squared_error',optimizer='adam')
RNN_Model_pos_y_node_7 = Sequential()
RNN_Model_pos_y_node_7.add(RNN(50,input_shape=(4,1)))
RNN_Model_pos_y_node_7.add(Dense(1))
RNN_Model_pos_y_node_7.compile(loss='mean_squared_error',optimizer='adam')
RNN_Model_speed_node_7 = Sequential()
RNN_Model_speed_node_7.add(RNN(50,input_shape=(4,1)))
RNN_Model_speed_node_7.add(Dense(1))
RNN_Model_speed_node_7.compile(loss='mean_squared_error',optimizer='adam')
RNN_Model_energy_node_7 = Sequential()
RNN_Model_energy_node_7.add(RNN(50,input_shape=(4,1)))
RNN_Model_energy_node_7.add(Dense(1))
RNN_Model_energy_node_7.compile(loss='mean_squared_error',optimizer='adam')

RNN_Model_pos_x_node_15 = Sequential()
RNN_Model_pos_x_node_15.add(RNN(50,input_shape=(4,1)))
RNN_Model_pos_x_node_15.add(Dense(1))
RNN_Model_pos_x_node_15.compile(loss='mean_squared_error',optimizer='adam')
RNN_Model_pos_y_node_15 = Sequential()
RNN_Model_pos_y_node_15.add(RNN(50,input_shape=(4,1)))
RNN_Model_pos_y_node_15.add(Dense(1))
RNN_Model_pos_y_node_15.compile(loss='mean_squared_error',optimizer='adam')
RNN_Model_speed_node_15 = Sequential()
RNN_Model_speed_node_15.add(RNN(50,input_shape=(4,1)))
RNN_Model_speed_node_15.add(Dense(1))
RNN_Model_speed_node_15.compile(loss='mean_squared_error',optimizer='adam')
RNN_Model_energy_node_15 = Sequential()
RNN_Model_energy_node_15.add(RNN(50,input_shape=(4,1)))
RNN_Model_energy_node_15.add(Dense(1))
RNN_Model_energy_node_15.compile(loss='mean_squared_error',optimizer='adam')

RNN_Model_pos_x_node_24 = Sequential()
RNN_Model_pos_x_node_24.add(RNN(50,input_shape=(4,1)))
RNN_Model_pos_x_node_24.add(Dense(1))
RNN_Model_pos_x_node_24.compile(loss='mean_squared_error',optimizer='adam')
RNN_Model_pos_y_node_24 = Sequential()
RNN_Model_pos_y_node_24.add(RNN(50,input_shape=(4,1)))
RNN_Model_pos_y_node_24.add(Dense(1))
RNN_Model_pos_y_node_24.compile(loss='mean_squared_error',optimizer='adam')
RNN_Model_speed_node_24 = Sequential()
RNN_Model_speed_node_24.add(RNN(50,input_shape=(4,1)))
RNN_Model_speed_node_24.add(Dense(1))
RNN_Model_speed_node_24.compile(loss='mean_squared_error',optimizer='adam')
RNN_Model_energy_node_24 = Sequential()
RNN_Model_energy_node_24.add(RNN(50,input_shape=(4,1)))
RNN_Model_energy_node_24.add(Dense(1))
RNN_Model_energy_node_24.compile(loss='mean_squared_error',optimizer='adam')

RNN_Model_pos_x_node_33 = Sequential()
RNN_Model_pos_x_node_33.add(RNN(50,input_shape=(4,1)))
RNN_Model_pos_x_node_33.add(Dense(1))
RNN_Model_pos_x_node_33.compile(loss='mean_squared_error',optimizer='adam')
RNN_Model_pos_y_node_33 = Sequential()
RNN_Model_pos_y_node_33.add(RNN(50,input_shape=(4,1)))
RNN_Model_pos_y_node_33.add(Dense(1))
RNN_Model_pos_y_node_33.compile(loss='mean_squared_error',optimizer='adam')
RNN_Model_speed_node_33 = Sequential()
RNN_Model_speed_node_33.add(RNN(50,input_shape=(4,1)))
RNN_Model_speed_node_33.add(Dense(1))
RNN_Model_speed_node_33.compile(loss='mean_squared_error',optimizer='adam')
RNN_Model_energy_node_33 = Sequential()
RNN_Model_energy_node_33.add(RNN(50,input_shape=(4,1)))
RNN_Model_energy_node_33.add(Dense(1))
RNN_Model_energy_node_33.compile(loss='mean_squared_error',optimizer='adam')

RNN_Model_pos_x_node_48 = Sequential()
RNN_Model_pos_x_node_48.add(RNN(50,input_shape=(4,1)))
RNN_Model_pos_x_node_48.add(Dense(1))
RNN_Model_pos_x_node_48.compile(loss='mean_squared_error',optimizer='adam')
RNN_Model_pos_y_node_48 = Sequential()
RNN_Model_pos_y_node_48.add(RNN(50,input_shape=(4,1)))
RNN_Model_pos_y_node_48.add(Dense(1))
RNN_Model_pos_y_node_48.compile(loss='mean_squared_error',optimizer='adam')
RNN_Model_speed_node_48 = Sequential()
RNN_Model_speed_node_48.add(RNN(50,input_shape=(4,1)))
RNN_Model_speed_node_48.add(Dense(1))
RNN_Model_speed_node_48.compile(loss='mean_squared_error',optimizer='adam')
RNN_Model_energy_node_48 = Sequential()
RNN_Model_energy_node_48.add(RNN(50,input_shape=(4,1)))
RNN_Model_energy_node_48.add(Dense(1))
RNN_Model_energy_node_48.compile(loss='mean_squared_error',optimizer='adam')

RNN_Model_pos_x_node_7.fit(X_training_data_reshaped_node_7,y_training_data_pos_x_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_pos_x_node_7),epochs=5,batch_size=10,verbose=1)
RNN_Model_pos_y_node_7.fit(X_training_data_reshaped_node_7,y_training_data_pos_y_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_pos_y_node_7),epochs=5,batch_size=10,verbose=1)
RNN_Model_speed_node_7.fit(X_training_data_reshaped_node_7,y_training_data_speed_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_speed_node_7),epochs=5,batch_size=10,verbose=1)
RNN_Model_energy_node_7.fit(X_training_data_reshaped_node_7,y_training_data_energy_node_7,validation_data=(X_testing_data_reshaped_node_7,y_testing_data_energy_node_7),epochs=5,batch_size=10,verbose=1)

RNN_Model_pos_x_node_15.fit(X_training_data_reshaped_node_15,y_training_data_pos_x_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_pos_x_node_15),epochs=5,batch_size=10,verbose=1)
RNN_Model_pos_y_node_15.fit(X_training_data_reshaped_node_15,y_training_data_pos_y_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_pos_y_node_15),epochs=5,batch_size=10,verbose=1)
RNN_Model_speed_node_15.fit(X_training_data_reshaped_node_15,y_training_data_speed_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_speed_node_15),epochs=5,batch_size=10,verbose=1)
RNN_Model_energy_node_15.fit(X_training_data_reshaped_node_15,y_training_data_energy_node_15,validation_data=(X_testing_data_reshaped_node_15,y_testing_data_energy_node_15),epochs=5,batch_size=10,verbose=1)

RNN_Model_pos_x_node_24.fit(X_training_data_reshaped_node_24,y_training_data_pos_x_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_pos_x_node_24),epochs=5,batch_size=10,verbose=1)
RNN_Model_pos_y_node_24.fit(X_training_data_reshaped_node_24,y_training_data_pos_y_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_pos_y_node_24),epochs=5,batch_size=10,verbose=1)
RNN_Model_speed_node_24.fit(X_training_data_reshaped_node_24,y_training_data_speed_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_speed_node_24),epochs=5,batch_size=10,verbose=1)
RNN_Model_energy_node_24.fit(X_training_data_reshaped_node_24,y_training_data_energy_node_24,validation_data=(X_testing_data_reshaped_node_24,y_testing_data_energy_node_24),epochs=5,batch_size=10,verbose=1)

RNN_Model_pos_x_node_33.fit(X_training_data_reshaped_node_33,y_training_data_pos_x_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_pos_x_node_33),epochs=5,batch_size=10,verbose=1)
RNN_Model_pos_y_node_33.fit(X_training_data_reshaped_node_33,y_training_data_pos_y_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_pos_y_node_33),epochs=5,batch_size=10,verbose=1)
RNN_Model_speed_node_33.fit(X_training_data_reshaped_node_33,y_training_data_speed_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_speed_node_33),epochs=5,batch_size=10,verbose=1)
RNN_Model_energy_node_33.fit(X_training_data_reshaped_node_33,y_training_data_energy_node_33,validation_data=(X_testing_data_reshaped_node_33,y_testing_data_energy_node_33),epochs=5,batch_size=10,verbose=1)

RNN_Model_pos_x_node_48.fit(X_training_data_reshaped_node_48,y_training_data_pos_x_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_pos_x_node_48),epochs=5,batch_size=10,verbose=1)
RNN_Model_pos_y_node_48.fit(X_training_data_reshaped_node_48,y_training_data_pos_y_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_pos_y_node_48),epochs=5,batch_size=10,verbose=1)
RNN_Model_speed_node_48.fit(X_training_data_reshaped_node_48,y_training_data_speed_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_speed_node_48),epochs=5,batch_size=10,verbose=1)
RNN_Model_energy_node_48.fit(X_training_data_reshaped_node_48,y_training_data_energy_node_48,validation_data=(X_testing_data_reshaped_node_48,y_testing_data_energy_node_48),epochs=5,batch_size=10,verbose=1)

Epoch 1/5
195/195 [==============================] - 2s 3ms/step - loss: 35325.5585 - val_loss: 24770.3125
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 30874.6596 - val_loss: 21970.3379
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 26765.3150 - val_loss: 19558.4434
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 24617.4794 - val_loss: 17417.2500
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 22049.6402 - val_loss: 15516.4297
Epoch 1/5
195/195 [==============================] - 2s 3ms/step - loss: 45306.2476 - val_loss: 22733.1602
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 35843.5286 - val_loss: 19817.4141
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 36205.0585 - val_loss: 17312.7637
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 31611.7394 - val_loss: 15095.2930
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 29392.0091 - val_loss: 13118.4805
Epoch 1/5
195/195 [==============================] - 2s 3ms/step - loss: 7.2964 - val_loss: 2.0146
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 0.6001 - val_loss: 0.2463
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 0.2137 - val_loss: 0.2433
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 0.2151 - val_loss: 0.2524
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 0.3076 - val_loss: 0.2427
Epoch 1/5
195/195 [==============================] - 2s 3ms/step - loss: 295701.9762 - val_loss: 1279.1305
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 271265.1138 - val_loss: 1568.2772
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 274104.8422 - val_loss: 2032.4894
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 268274.7581 - val_loss: 2667.7510
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 252182.6865 - val_loss: 3466.6111
Epoch 1/5
195/195 [==============================] - 2s 3ms/step - loss: 59057.3541 - val_loss: 34383.4375
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 52966.8704 - val_loss: 30773.1680
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 50022.7346 - val_loss: 27584.9531
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 44132.5715 - val_loss: 24689.2930
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 41523.2333 - val_loss: 22058.9629
Epoch 1/5
195/195 [==============================] - 2s 3ms/step - loss: 63965.5932 - val_loss: 46655.5703
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 54975.3224 - val_loss: 42221.4297
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 51260.0499 - val_loss: 38267.5273
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 47978.4701 - val_loss: 34650.5938
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 43866.9023 - val_loss: 31305.8203
Epoch 1/5
195/195 [==============================] - 2s 3ms/step - loss: 2.9667 - val_loss: 0.7005
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 0.2373 - val_loss: 0.6446
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 0.1280 - val_loss: 0.7329
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 0.2492 - val_loss: 0.6474
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 0.1571 - val_loss: 0.7369
Epoch 1/5
195/195 [==============================] - 2s 3ms/step - loss: 526512.3029 - val_loss: 249892.4219
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 481154.2285 - val_loss: 244248.6719
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 477511.8254 - val_loss: 239193.9844
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 484345.5665 - val_loss: 234461.4375
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 467312.8538 - val_loss: 229972.5156
Epoch 1/5
195/195 [==============================] - 2s 4ms/step - loss: 103137.6766 - val_loss: 86202.1016
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 92020.9887 - val_loss: 80566.4141
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 85306.3616 - val_loss: 75465.3047
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 79637.3396 - val_loss: 70720.9375
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 77543.5837 - val_loss: 66282.3203
Epoch 1/5
195/195 [==============================] - 2s 4ms/step - loss: 20518.5443 - val_loss: 18179.1328
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 17198.4211 - val_loss: 16198.4102
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 14898.2108 - val_loss: 14558.7695
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 13548.9938 - val_loss: 13160.4971
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 12551.9667 - val_loss: 11985.5742
Epoch 1/5
195/195 [==============================] - 2s 3ms/step - loss: 3.6574 - val_loss: 3.9913
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 0.4361 - val_loss: 1.6787
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 0.1507 - val_loss: 1.9110
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 0.1519 - val_loss: 1.5988
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 0.1098 - val_loss: 1.8256
Epoch 1/5
195/195 [==============================] - 14s 3ms/step - loss: 2467618.5855 - val_loss: 1044183.8750
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 2332027.7717 - val_loss: 1025429.0000
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 2349232.1429 - val_loss: 1008140.0000
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 2364383.8648 - val_loss: 991420.8750
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 2261794.5510 - val_loss: 975093.1875
Epoch 1/5
195/195 [==============================] - 2s 3ms/step - loss: 83153.8062 - val_loss: 53558.7148
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 77046.6269 - val_loss: 49142.2227
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 75073.7207 - val_loss: 45179.6172
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 66940.3950 - val_loss: 41513.4727
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 61871.3788 - val_loss: 38098.8984
Epoch 1/5
195/195 [==============================] - 2s 3ms/step - loss: 76218.2216 - val_loss: 66062.8828
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 68656.1559 - val_loss: 61134.3359
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 63947.7706 - val_loss: 56671.3906
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 60070.5436 - val_loss: 52522.3984
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 54715.7051 - val_loss: 48662.5469
Epoch 1/5
195/195 [==============================] - 2s 4ms/step - loss: 4.6424 - val_loss: 0.5427
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 0.3412 - val_loss: 0.6157
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 0.2655 - val_loss: 0.5751
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 0.1305 - val_loss: 0.7043
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 0.1746 - val_loss: 0.6772
Epoch 1/5
195/195 [==============================] - 2s 4ms/step - loss: 726147.9158 - val_loss: 260642.7031
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 684873.3412 - val_loss: 251983.2969
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 699288.2398 - val_loss: 243849.6875
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 667886.4515 - val_loss: 236091.3438
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 689091.7305 - val_loss: 228637.8281
Epoch 1/5
195/195 [==============================] - 2s 3ms/step - loss: 152755.1997 - val_loss: 132516.2344
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 139988.1348 - val_loss: 124854.2188
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 131881.4405 - val_loss: 117825.1484
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 125341.5002 - val_loss: 111185.7109
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 119385.5277 - val_loss: 104863.8984
Epoch 1/5
195/195 [==============================] - 2s 3ms/step - loss: 22087.9635 - val_loss: 18291.0645
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 18007.5633 - val_loss: 15638.8926
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 15442.2205 - val_loss: 13354.6191
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 13184.9923 - val_loss: 11346.5967
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 11196.8975 - val_loss: 9576.8037
Epoch 1/5
195/195 [==============================] - 2s 3ms/step - loss: 5.1649 - val_loss: 3.4066
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 0.1182 - val_loss: 2.4327
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 0.1076 - val_loss: 2.2536
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 0.1085 - val_loss: 2.4892
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 0.0411 - val_loss: 2.7523
Epoch 1/5
195/195 [==============================] - 2s 4ms/step - loss: 4227943.7334 - val_loss: 411798.7812
Epoch 2/5
195/195 [==============================] - 0s 2ms/step - loss: 4155603.9298 - val_loss: 398502.2188
Epoch 3/5
195/195 [==============================] - 0s 2ms/step - loss: 4137536.7755 - val_loss: 385990.4375
Epoch 4/5
195/195 [==============================] - 0s 2ms/step - loss: 4007453.3929 - val_loss: 373923.6562
Epoch 5/5
195/195 [==============================] - 0s 2ms/step - loss: 4052765.8406 - val_loss: 362146.3125

<tensorflow.python.keras.callbacks.History at 0x1960ac13820>

train_predict_RNN_Model_pos_x_node_7 = RNN_Model_pos_x_node_7.predict(X_training_data_reshaped_node_7)
test_predict_RNN_Model_pos_x_node_7 = RNN_Model_pos_x_node_7.predict(X_testing_data_reshaped_node_7)
train_predict_RNN_Model_pos_y_node_7 = RNN_Model_pos_y_node_7.predict(X_training_data_reshaped_node_7)
test_predict_RNN_Model_pos_y_node_7 = RNN_Model_pos_y_node_7.predict(X_testing_data_reshaped_node_7)
train_predict_RNN_Model_speed_node_7 = RNN_Model_speed_node_7.predict(X_training_data_reshaped_node_7)
test_predict_RNN_Model_speed_node_7 = RNN_Model_speed_node_7.predict(X_testing_data_reshaped_node_7)
train_predict_RNN_Model_energy_node_7 = RNN_Model_energy_node_7.predict(X_training_data_reshaped_node_7)
test_predict_RNN_Model_energy_node_7 = RNN_Model_energy_node_7.predict(X_testing_data_reshaped_node_7)

train_predict_RNN_Model_pos_x_node_15 = RNN_Model_pos_x_node_15.predict(X_training_data_reshaped_node_15)
test_predict_RNN_Model_pos_x_node_15 = RNN_Model_pos_x_node_15.predict(X_testing_data_reshaped_node_15)
train_predict_RNN_Model_pos_y_node_15 = RNN_Model_pos_y_node_15.predict(X_training_data_reshaped_node_15)
test_predict_RNN_Model_pos_y_node_15 = RNN_Model_pos_y_node_15.predict(X_testing_data_reshaped_node_15)
train_predict_RNN_Model_speed_node_15 = RNN_Model_speed_node_15.predict(X_training_data_reshaped_node_15)
test_predict_RNN_Model_speed_node_15 = RNN_Model_speed_node_15.predict(X_testing_data_reshaped_node_15)
train_predict_RNN_Model_energy_node_15 = RNN_Model_energy_node_15.predict(X_training_data_reshaped_node_15)
test_predict_RNN_Model_energy_node_15 = RNN_Model_energy_node_15.predict(X_testing_data_reshaped_node_15)

train_predict_RNN_Model_pos_x_node_24 = RNN_Model_pos_x_node_24.predict(X_training_data_reshaped_node_24)
test_predict_RNN_Model_pos_x_node_24 = RNN_Model_pos_x_node_24.predict(X_testing_data_reshaped_node_24)
train_predict_RNN_Model_pos_y_node_24 = RNN_Model_pos_y_node_24.predict(X_training_data_reshaped_node_24)
test_predict_RNN_Model_pos_y_node_24 = RNN_Model_pos_y_node_24.predict(X_testing_data_reshaped_node_24)
train_predict_RNN_Model_speed_node_24 = RNN_Model_speed_node_24.predict(X_training_data_reshaped_node_24)
test_predict_RNN_Model_speed_node_24 = RNN_Model_speed_node_24.predict(X_testing_data_reshaped_node_24)
train_predict_RNN_Model_energy_node_24 = RNN_Model_energy_node_24.predict(X_training_data_reshaped_node_24)
test_predict_RNN_Model_energy_node_24 = RNN_Model_energy_node_24.predict(X_testing_data_reshaped_node_24)

train_predict_RNN_Model_pos_x_node_33 = RNN_Model_pos_x_node_33.predict(X_training_data_reshaped_node_33)
test_predict_RNN_Model_pos_x_node_33 = RNN_Model_pos_x_node_33.predict(X_testing_data_reshaped_node_33)
train_predict_RNN_Model_pos_y_node_33 = RNN_Model_pos_y_node_33.predict(X_training_data_reshaped_node_33)
test_predict_RNN_Model_pos_y_node_33 = RNN_Model_pos_y_node_33.predict(X_testing_data_reshaped_node_33)
train_predict_RNN_Model_speed_node_33 = RNN_Model_speed_node_33.predict(X_training_data_reshaped_node_33)
test_predict_RNN_Model_speed_node_33 = RNN_Model_speed_node_33.predict(X_testing_data_reshaped_node_33)
train_predict_RNN_Model_energy_node_33 = RNN_Model_energy_node_33.predict(X_training_data_reshaped_node_33)
test_predict_RNN_Model_energy_node_33 = RNN_Model_energy_node_33.predict(X_testing_data_reshaped_node_33)

train_predict_RNN_Model_pos_x_node_48 = RNN_Model_pos_x_node_48.predict(X_training_data_reshaped_node_48)
test_predict_RNN_Model_pos_x_node_48 = RNN_Model_pos_x_node_48.predict(X_testing_data_reshaped_node_48)
train_predict_RNN_Model_pos_y_node_48 = RNN_Model_pos_y_node_48.predict(X_training_data_reshaped_node_48)
test_predict_RNN_Model_pos_y_node_48 = RNN_Model_pos_y_node_48.predict(X_testing_data_reshaped_node_48)
train_predict_RNN_Model_speed_node_48 = RNN_Model_speed_node_48.predict(X_training_data_reshaped_node_48)
test_predict_RNN_Model_speed_node_48 = RNN_Model_speed_node_48.predict(X_testing_data_reshaped_node_48)
train_predict_RNN_Model_energy_node_48 = RNN_Model_energy_node_48.predict(X_training_data_reshaped_node_48)
test_predict_RNN_Model_energy_node_48 = RNN_Model_energy_node_48.predict(X_testing_data_reshaped_node_48)

RMSE

print("\n\nRMSE on Training Data by RNN: ")
print("======================================\n\n")

print("\n\nRMSE of Node 7: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_7,train_predict_RNN_Model_pos_x_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_7,train_predict_RNN_Model_pos_y_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_7,train_predict_RNN_Model_speed_node_7)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_7,train_predict_RNN_Model_energy_node_7)))
      
print("\n\nRMSE of Node 15: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_15,train_predict_RNN_Model_pos_x_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_15,train_predict_RNN_Model_pos_y_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_15,train_predict_RNN_Model_speed_node_15)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_15,train_predict_RNN_Model_energy_node_15)))
      
print("\n\nRMSE of Node 24: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_24,train_predict_RNN_Model_pos_x_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_24,train_predict_RNN_Model_pos_y_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_24,train_predict_RNN_Model_speed_node_24)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_24,train_predict_RNN_Model_energy_node_24)))

print("\n\nRMSE of Node 33: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_33,train_predict_RNN_Model_pos_x_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_33,train_predict_RNN_Model_pos_y_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_33,train_predict_RNN_Model_speed_node_33)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_33,train_predict_RNN_Model_energy_node_33)))
      
print("\n\nRMSE of Node 48: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x_node_48,train_predict_RNN_Model_pos_x_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y_node_48,train_predict_RNN_Model_pos_y_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_speed_node_48,train_predict_RNN_Model_speed_node_48)))
print(math.sqrt(mean_squared_error(y_training_data_energy_node_48,train_predict_RNN_Model_energy_node_48)))

print("\n\nRMSE on Testing Data by RNN: ")
print("=====================================\n\n")
      
print("\n\nRMSE of Node 7: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_RNN_Model_pos_x_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_RNN_Model_pos_y_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_RNN_Model_speed_node_7)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_RNN_Model_energy_node_7)))
      
print("\n\nRMSE of Node 15: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_RNN_Model_pos_x_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_RNN_Model_pos_y_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_RNN_Model_speed_node_15)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_RNN_Model_energy_node_15)))
     
print("\n\nRMSE of Node 24: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_RNN_Model_pos_x_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_24,test_predict_RNN_Model_pos_y_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_RNN_Model_speed_node_24)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_RNN_Model_energy_node_24)))
      
print("\n\nRMSE of Node 33: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_RNN_Model_pos_x_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_RNN_Model_pos_y_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_RNN_Model_speed_node_33)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_RNN_Model_energy_node_33)))
      
print("\n\nRMSE of Node 48: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_RNN_Model_pos_x_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_RNN_Model_pos_y_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_RNN_Model_speed_node_48)))
print(math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_RNN_Model_energy_node_48)))

RMSE on Training Data by RNN: 
======================================




RMSE of Node 7: 
======================================


143.0418718688773
166.37545986808323
0.49993825282049803
495.4853091525583


RMSE of Node 15: 
======================================


197.17589272813044
202.22276696261034
0.4042618188928671
677.038040263439


RMSE of Node 24: 
======================================


270.75707165760736
107.31615451576619
0.36780982490512065
1515.076221154328


RMSE of Node 33: 
======================================


241.30736189002354
228.23623836001252
0.4097690763561436
813.3903125508962


RMSE of Node 48: 
======================================


337.0478205552667
99.41730717444513
0.29344807005950124
1996.0531703611189


RMSE on Testing Data by RNN: 
=====================================




RMSE of Node 7: 
======================================


124.56495459719021
114.53593711893676
0.4926025771755116
58.87792915288162


RMSE of Node 15: 
======================================


148.522614924966
176.93451053857785
0.8584550146744845
479.5544453226019


RMSE of Node 24: 
======================================


257.4535214800704
109.4786457962932
1.351143446594122
987.4681164071391


RMSE of Node 33: 
======================================


195.18939770976954
220.59589685668757
0.8229388886971586
478.1609091476392


RMSE of Node 48: 
======================================


323.8269430504975
97.86114465471238
1.6590009256306597
601.7859475573283

Graph

print("\n\nGraph of Node 7: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_7)
plt.plot(test_predict_RNN_Model_pos_x_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_7)
plt.plot(test_predict_RNN_Model_pos_y_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_7)
plt.plot(test_predict_RNN_Model_speed_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_7)
plt.plot(test_predict_RNN_Model_energy_node_7)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 15: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_15)
plt.plot(test_predict_RNN_Model_pos_x_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_15)
plt.plot(test_predict_RNN_Model_pos_y_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_15)
plt.plot(test_predict_RNN_Model_speed_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_15)
plt.plot(test_predict_RNN_Model_energy_node_15)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 24: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_24)
plt.plot(test_predict_RNN_Model_pos_x_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_24)
plt.plot(test_predict_RNN_Model_pos_y_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_24)
plt.plot(test_predict_RNN_Model_speed_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_24)
plt.plot(test_predict_RNN_Model_energy_node_24)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 33: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_33)
plt.plot(test_predict_RNN_Model_pos_x_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_33)
plt.plot(test_predict_RNN_Model_pos_y_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_33)
plt.plot(test_predict_RNN_Model_speed_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_33)
plt.plot(test_predict_RNN_Model_energy_node_33)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

print("\n\nGraph of Node 48: ")
print("======================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x_node_48)
plt.plot(test_predict_RNN_Model_pos_x_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y_node_48)
plt.plot(test_predict_RNN_Model_pos_y_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed_node_48)
plt.plot(test_predict_RNN_Model_speed_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy_node_48)
plt.plot(test_predict_RNN_Model_energy_node_48)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

Graph of Node 7: 
======================================

Graph of Node 15: 
======================================

Graph of Node 24: 
======================================

Graph of Node 33: 
======================================

Graph of Node 48: 
======================================

====================================================================================

Bar Graph - RMSE of All Single Models

====================================================================================

print("\n\n===============")
print("RMSE of Node 7: ")
print("===============\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_Stacked_LSTM_Model_pos_x_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_CNN_LSTM_Model_pos_x_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_LSTM_Model_pos_x_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_BiDirectonal_LSTM_Model_pos_x_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_GRU_Model_pos_x_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_RNN_Model_pos_x_node_7)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_Stacked_LSTM_Model_pos_y_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_CNN_LSTM_Model_pos_y_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_LSTM_Model_pos_y_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_BiDirectonal_LSTM_Model_pos_y_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_GRU_Model_pos_y_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_RNN_Model_pos_y_node_7)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_Stacked_LSTM_Model_speed_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_CNN_LSTM_Model_speed_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_LSTM_Model_speed_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_BiDirectonal_LSTM_Model_speed_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_GRU_Model_speed_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_RNN_Model_speed_node_7)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_Stacked_LSTM_Model_energy_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_CNN_LSTM_Model_energy_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_LSTM_Model_energy_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_BiDirectonal_LSTM_Model_energy_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_GRU_Model_energy_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_RNN_Model_energy_node_7)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.8)
ax.bar(X, data[1], color = 'purple', width = 0.6)
ax.bar(X, data[2], color = 'red', width = 0.4)
ax.bar(X, data[3], color = 'green', width = 0.2)
ax.legend(['POS X','POS Y','SPEED','ENERGY'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n===============")
print("RMSE of Node 15: ")
print("===============\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_Stacked_LSTM_Model_pos_x_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_CNN_LSTM_Model_pos_x_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_LSTM_Model_pos_x_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_BiDirectonal_LSTM_Model_pos_x_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_GRU_Model_pos_x_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_RNN_Model_pos_x_node_15)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_Stacked_LSTM_Model_pos_y_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_CNN_LSTM_Model_pos_y_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_LSTM_Model_pos_y_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_BiDirectonal_LSTM_Model_pos_y_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_GRU_Model_pos_y_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_RNN_Model_pos_y_node_15)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_Stacked_LSTM_Model_speed_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_CNN_LSTM_Model_speed_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_LSTM_Model_speed_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_BiDirectonal_LSTM_Model_speed_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_GRU_Model_speed_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_RNN_Model_speed_node_15)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_Stacked_LSTM_Model_energy_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_CNN_LSTM_Model_energy_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_LSTM_Model_energy_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_BiDirectonal_LSTM_Model_energy_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_GRU_Model_energy_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_RNN_Model_energy_node_15)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.8)
ax.bar(X, data[1], color = 'purple', width = 0.6)
ax.bar(X, data[2], color = 'red', width = 0.4)
ax.bar(X, data[3], color = 'green', width = 0.2)
ax.legend(['POS X','POS Y','SPEED','ENERGY'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n===============")
print("RMSE of Node 24: ")
print("===============\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_Stacked_LSTM_Model_pos_x_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_CNN_LSTM_Model_pos_x_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_LSTM_Model_pos_x_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_BiDirectonal_LSTM_Model_pos_x_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_GRU_Model_pos_x_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_RNN_Model_pos_x_node_24)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_Stacked_LSTM_Model_pos_y_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_CNN_LSTM_Model_pos_y_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_LSTM_Model_pos_y_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_BiDirectonal_LSTM_Model_pos_y_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_GRU_Model_pos_y_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_RNN_Model_pos_y_node_24)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_Stacked_LSTM_Model_speed_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_CNN_LSTM_Model_speed_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_LSTM_Model_speed_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_BiDirectonal_LSTM_Model_speed_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_GRU_Model_speed_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_RNN_Model_speed_node_24)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_Stacked_LSTM_Model_energy_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_CNN_LSTM_Model_energy_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_LSTM_Model_energy_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_BiDirectonal_LSTM_Model_energy_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_GRU_Model_energy_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_RNN_Model_energy_node_24)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.8)
ax.bar(X, data[1], color = 'purple', width = 0.6)
ax.bar(X, data[2], color = 'red', width = 0.4)
ax.bar(X, data[3], color = 'green', width = 0.2)
ax.legend(['POS X','POS Y','SPEED','ENERGY'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n===============")
print("RMSE of Node 33: ")
print("===============\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_Stacked_LSTM_Model_pos_x_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_CNN_LSTM_Model_pos_x_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_LSTM_Model_pos_x_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_BiDirectonal_LSTM_Model_pos_x_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_GRU_Model_pos_x_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_RNN_Model_pos_x_node_33)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_Stacked_LSTM_Model_pos_y_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_CNN_LSTM_Model_pos_y_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_LSTM_Model_pos_y_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_BiDirectonal_LSTM_Model_pos_y_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_GRU_Model_pos_y_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_RNN_Model_pos_y_node_33)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_Stacked_LSTM_Model_speed_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_CNN_LSTM_Model_speed_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_LSTM_Model_speed_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_BiDirectonal_LSTM_Model_speed_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_GRU_Model_speed_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_RNN_Model_speed_node_33)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_Stacked_LSTM_Model_energy_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_CNN_LSTM_Model_energy_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_LSTM_Model_energy_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_BiDirectonal_LSTM_Model_energy_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_GRU_Model_energy_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_RNN_Model_energy_node_33)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.8)
ax.bar(X, data[1], color = 'purple', width = 0.6)
ax.bar(X, data[2], color = 'red', width = 0.4)
ax.bar(X, data[3], color = 'green', width = 0.2)
ax.legend(['POS X','POS Y','SPEED','ENERGY'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n===============")
print("RMSE of Node 48: ")
print("===============\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_Stacked_LSTM_Model_pos_x_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_CNN_LSTM_Model_pos_x_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_LSTM_Model_pos_x_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_BiDirectonal_LSTM_Model_pos_x_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_GRU_Model_pos_x_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_RNN_Model_pos_x_node_48)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_Stacked_LSTM_Model_pos_y_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_CNN_LSTM_Model_pos_y_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_LSTM_Model_pos_y_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_BiDirectonal_LSTM_Model_pos_y_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_GRU_Model_pos_y_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_RNN_Model_pos_y_node_48)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_Stacked_LSTM_Model_speed_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_CNN_LSTM_Model_speed_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_LSTM_Model_speed_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_BiDirectonal_LSTM_Model_speed_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_GRU_Model_speed_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_RNN_Model_speed_node_48)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_Stacked_LSTM_Model_energy_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_CNN_LSTM_Model_energy_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_LSTM_Model_energy_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_BiDirectonal_LSTM_Model_energy_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_GRU_Model_energy_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_RNN_Model_energy_node_48)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.8)
ax.bar(X, data[1], color = 'purple', width = 0.6)
ax.bar(X, data[2], color = 'red', width = 0.4)
ax.bar(X, data[3], color = 'green', width = 0.2)
ax.legend(['POS X','POS Y','SPEED','ENERGY'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

===============
RMSE of Node 7: 
===============

===============
RMSE of Node 15: 
===============

===============
RMSE of Node 24: 
===============

===============
RMSE of Node 33: 
===============

===============
RMSE of Node 48: 
===============

!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

Approach 2 - Multiple Training

!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

Load Dataset

path = ('Datasets/Multiple Dataset')
data = [os.path.join(dp, f) for dp, dn, filenames in os.walk(path) for f in filenames if os.path.splitext(f)[1] == '.csv']

print("\n\nName of Datasets that are Used:")
print("===============================\n\n")
for i in data:
    print(i)

Name of Datasets that are Used:
===============================


Datasets/Multiple Dataset\Hig-DR\node_0.csv
Datasets/Multiple Dataset\Hig-DR\node_1.csv
Datasets/Multiple Dataset\Hig-DR\node_10.csv
Datasets/Multiple Dataset\Hig-DR\node_11.csv
Datasets/Multiple Dataset\Hig-DR\node_12.csv
Datasets/Multiple Dataset\Hig-DR\node_13.csv
Datasets/Multiple Dataset\Hig-DR\node_14.csv
Datasets/Multiple Dataset\Hig-DR\node_15.csv
Datasets/Multiple Dataset\Hig-DR\node_16.csv
Datasets/Multiple Dataset\Hig-DR\node_17.csv
Datasets/Multiple Dataset\Hig-DR\node_18.csv
Datasets/Multiple Dataset\Hig-DR\node_19.csv
Datasets/Multiple Dataset\Hig-DR\node_2.csv
Datasets/Multiple Dataset\Hig-DR\node_20.csv
Datasets/Multiple Dataset\Hig-DR\node_21.csv
Datasets/Multiple Dataset\Hig-DR\node_22.csv
Datasets/Multiple Dataset\Hig-DR\node_23.csv
Datasets/Multiple Dataset\Hig-DR\node_24.csv
Datasets/Multiple Dataset\Hig-DR\node_25.csv
Datasets/Multiple Dataset\Hig-DR\node_26.csv
Datasets/Multiple Dataset\Hig-DR\node_27.csv
Datasets/Multiple Dataset\Hig-DR\node_28.csv
Datasets/Multiple Dataset\Hig-DR\node_29.csv
Datasets/Multiple Dataset\Hig-DR\node_3.csv
Datasets/Multiple Dataset\Hig-DR\node_30.csv
Datasets/Multiple Dataset\Hig-DR\node_31.csv
Datasets/Multiple Dataset\Hig-DR\node_32.csv
Datasets/Multiple Dataset\Hig-DR\node_33.csv
Datasets/Multiple Dataset\Hig-DR\node_34.csv
Datasets/Multiple Dataset\Hig-DR\node_35.csv
Datasets/Multiple Dataset\Hig-DR\node_36.csv
Datasets/Multiple Dataset\Hig-DR\node_37.csv
Datasets/Multiple Dataset\Hig-DR\node_38.csv
Datasets/Multiple Dataset\Hig-DR\node_39.csv
Datasets/Multiple Dataset\Hig-DR\node_4.csv
Datasets/Multiple Dataset\Hig-DR\node_40.csv
Datasets/Multiple Dataset\Hig-DR\node_41.csv
Datasets/Multiple Dataset\Hig-DR\node_42.csv
Datasets/Multiple Dataset\Hig-DR\node_43.csv
Datasets/Multiple Dataset\Hig-DR\node_44.csv
Datasets/Multiple Dataset\Hig-DR\node_45.csv
Datasets/Multiple Dataset\Hig-DR\node_46.csv
Datasets/Multiple Dataset\Hig-DR\node_47.csv
Datasets/Multiple Dataset\Hig-DR\node_48.csv
Datasets/Multiple Dataset\Hig-DR\node_49.csv
Datasets/Multiple Dataset\Hig-DR\node_5.csv
Datasets/Multiple Dataset\Hig-DR\node_50.csv
Datasets/Multiple Dataset\Hig-DR\node_51.csv
Datasets/Multiple Dataset\Hig-DR\node_52.csv
Datasets/Multiple Dataset\Hig-DR\node_53.csv
Datasets/Multiple Dataset\Hig-DR\node_54.csv
Datasets/Multiple Dataset\Hig-DR\node_55.csv
Datasets/Multiple Dataset\Hig-DR\node_56.csv
Datasets/Multiple Dataset\Hig-DR\node_57.csv
Datasets/Multiple Dataset\Hig-DR\node_58.csv
Datasets/Multiple Dataset\Hig-DR\node_59.csv
Datasets/Multiple Dataset\Hig-DR\node_6.csv
Datasets/Multiple Dataset\Hig-DR\node_7.csv
Datasets/Multiple Dataset\Hig-DR\node_8.csv
Datasets/Multiple Dataset\Hig-DR\node_9.csv
Datasets/Multiple Dataset\Low-DR\node_0.csv
Datasets/Multiple Dataset\Low-DR\node_1.csv
Datasets/Multiple Dataset\Low-DR\node_10.csv
Datasets/Multiple Dataset\Low-DR\node_11.csv
Datasets/Multiple Dataset\Low-DR\node_12.csv
Datasets/Multiple Dataset\Low-DR\node_13.csv
Datasets/Multiple Dataset\Low-DR\node_14.csv
Datasets/Multiple Dataset\Low-DR\node_15.csv
Datasets/Multiple Dataset\Low-DR\node_16.csv
Datasets/Multiple Dataset\Low-DR\node_17.csv
Datasets/Multiple Dataset\Low-DR\node_18.csv
Datasets/Multiple Dataset\Low-DR\node_19.csv
Datasets/Multiple Dataset\Low-DR\node_2.csv
Datasets/Multiple Dataset\Low-DR\node_20.csv
Datasets/Multiple Dataset\Low-DR\node_21.csv
Datasets/Multiple Dataset\Low-DR\node_22.csv
Datasets/Multiple Dataset\Low-DR\node_23.csv
Datasets/Multiple Dataset\Low-DR\node_24.csv
Datasets/Multiple Dataset\Low-DR\node_25.csv
Datasets/Multiple Dataset\Low-DR\node_26.csv
Datasets/Multiple Dataset\Low-DR\node_27.csv
Datasets/Multiple Dataset\Low-DR\node_28.csv
Datasets/Multiple Dataset\Low-DR\node_29.csv
Datasets/Multiple Dataset\Low-DR\node_3.csv
Datasets/Multiple Dataset\Low-DR\node_30.csv
Datasets/Multiple Dataset\Low-DR\node_31.csv
Datasets/Multiple Dataset\Low-DR\node_32.csv
Datasets/Multiple Dataset\Low-DR\node_33.csv
Datasets/Multiple Dataset\Low-DR\node_34.csv
Datasets/Multiple Dataset\Low-DR\node_35.csv
Datasets/Multiple Dataset\Low-DR\node_36.csv
Datasets/Multiple Dataset\Low-DR\node_37.csv
Datasets/Multiple Dataset\Low-DR\node_38.csv
Datasets/Multiple Dataset\Low-DR\node_39.csv
Datasets/Multiple Dataset\Low-DR\node_4.csv
Datasets/Multiple Dataset\Low-DR\node_40.csv
Datasets/Multiple Dataset\Low-DR\node_41.csv
Datasets/Multiple Dataset\Low-DR\node_42.csv
Datasets/Multiple Dataset\Low-DR\node_43.csv
Datasets/Multiple Dataset\Low-DR\node_44.csv
Datasets/Multiple Dataset\Low-DR\node_45.csv
Datasets/Multiple Dataset\Low-DR\node_46.csv
Datasets/Multiple Dataset\Low-DR\node_47.csv
Datasets/Multiple Dataset\Low-DR\node_48.csv
Datasets/Multiple Dataset\Low-DR\node_49.csv
Datasets/Multiple Dataset\Low-DR\node_5.csv
Datasets/Multiple Dataset\Low-DR\node_50.csv
Datasets/Multiple Dataset\Low-DR\node_51.csv
Datasets/Multiple Dataset\Low-DR\node_52.csv
Datasets/Multiple Dataset\Low-DR\node_53.csv
Datasets/Multiple Dataset\Low-DR\node_54.csv
Datasets/Multiple Dataset\Low-DR\node_55.csv
Datasets/Multiple Dataset\Low-DR\node_56.csv
Datasets/Multiple Dataset\Low-DR\node_57.csv
Datasets/Multiple Dataset\Low-DR\node_58.csv
Datasets/Multiple Dataset\Low-DR\node_59.csv
Datasets/Multiple Dataset\Low-DR\node_6.csv
Datasets/Multiple Dataset\Low-DR\node_7.csv
Datasets/Multiple Dataset\Low-DR\node_8.csv
Datasets/Multiple Dataset\Low-DR\node_9.csv
Datasets/Multiple Dataset\Med-DR\node_0.csv
Datasets/Multiple Dataset\Med-DR\node_1.csv
Datasets/Multiple Dataset\Med-DR\node_10.csv
Datasets/Multiple Dataset\Med-DR\node_11.csv
Datasets/Multiple Dataset\Med-DR\node_12.csv
Datasets/Multiple Dataset\Med-DR\node_13.csv
Datasets/Multiple Dataset\Med-DR\node_14.csv
Datasets/Multiple Dataset\Med-DR\node_15.csv
Datasets/Multiple Dataset\Med-DR\node_16.csv
Datasets/Multiple Dataset\Med-DR\node_17.csv
Datasets/Multiple Dataset\Med-DR\node_18.csv
Datasets/Multiple Dataset\Med-DR\node_19.csv
Datasets/Multiple Dataset\Med-DR\node_2.csv
Datasets/Multiple Dataset\Med-DR\node_20.csv
Datasets/Multiple Dataset\Med-DR\node_21.csv
Datasets/Multiple Dataset\Med-DR\node_22.csv
Datasets/Multiple Dataset\Med-DR\node_23.csv
Datasets/Multiple Dataset\Med-DR\node_24.csv
Datasets/Multiple Dataset\Med-DR\node_25.csv
Datasets/Multiple Dataset\Med-DR\node_26.csv
Datasets/Multiple Dataset\Med-DR\node_27.csv
Datasets/Multiple Dataset\Med-DR\node_28.csv
Datasets/Multiple Dataset\Med-DR\node_29.csv
Datasets/Multiple Dataset\Med-DR\node_3.csv
Datasets/Multiple Dataset\Med-DR\node_30.csv
Datasets/Multiple Dataset\Med-DR\node_31.csv
Datasets/Multiple Dataset\Med-DR\node_32.csv
Datasets/Multiple Dataset\Med-DR\node_33.csv
Datasets/Multiple Dataset\Med-DR\node_34.csv
Datasets/Multiple Dataset\Med-DR\node_35.csv
Datasets/Multiple Dataset\Med-DR\node_36.csv
Datasets/Multiple Dataset\Med-DR\node_37.csv
Datasets/Multiple Dataset\Med-DR\node_38.csv
Datasets/Multiple Dataset\Med-DR\node_39.csv
Datasets/Multiple Dataset\Med-DR\node_4.csv
Datasets/Multiple Dataset\Med-DR\node_40.csv
Datasets/Multiple Dataset\Med-DR\node_41.csv
Datasets/Multiple Dataset\Med-DR\node_42.csv
Datasets/Multiple Dataset\Med-DR\node_43.csv
Datasets/Multiple Dataset\Med-DR\node_44.csv
Datasets/Multiple Dataset\Med-DR\node_45.csv
Datasets/Multiple Dataset\Med-DR\node_46.csv
Datasets/Multiple Dataset\Med-DR\node_47.csv
Datasets/Multiple Dataset\Med-DR\node_48.csv
Datasets/Multiple Dataset\Med-DR\node_49.csv
Datasets/Multiple Dataset\Med-DR\node_5.csv
Datasets/Multiple Dataset\Med-DR\node_50.csv
Datasets/Multiple Dataset\Med-DR\node_51.csv
Datasets/Multiple Dataset\Med-DR\node_52.csv
Datasets/Multiple Dataset\Med-DR\node_53.csv
Datasets/Multiple Dataset\Med-DR\node_54.csv
Datasets/Multiple Dataset\Med-DR\node_55.csv
Datasets/Multiple Dataset\Med-DR\node_56.csv
Datasets/Multiple Dataset\Med-DR\node_57.csv
Datasets/Multiple Dataset\Med-DR\node_58.csv
Datasets/Multiple Dataset\Med-DR\node_59.csv
Datasets/Multiple Dataset\Med-DR\node_6.csv
Datasets/Multiple Dataset\Med-DR\node_7.csv
Datasets/Multiple Dataset\Med-DR\node_8.csv
Datasets/Multiple Dataset\Med-DR\node_9.csv

all_data_training = pd.DataFrame()
all_data_testing = pd.DataFrame()
for i in data:
    sample_data = pd .read_csv(i)
    all_data_training = all_data_training.append(sample_data.head(650))
    all_data_testing = all_data_testing.append(sample_data[650:750])

all_data_training = all_data_training.drop("Time", axis = 1)
all_data_training = all_data_training.drop("Node", axis = 1)
all_data_training.reset_index(drop=True, inplace=True)

all_data_testing = all_data_testing.drop("Time", axis = 1)
all_data_testing = all_data_testing.drop("Node", axis = 1)
all_data_testing.reset_index(drop=True, inplace=True)

print("\n\nMain Dataset that is Used:")
print("==========================\n\n")
print("Training Dataset:\n\n")
print(all_data_training)
print("\n\nTesting Dataset:\n\n")
print(all_data_testing)

Main Dataset that is Used:
==========================


Training Dataset:


          pos_x    pos_y     speed      energy
0       307.922  503.508  0.000000  121.188655
1       307.871  503.345  1.974358  120.165500
2       306.494  504.296  1.974358  119.142345
3       305.116  505.246  1.974358  118.119190
4       303.738  506.197  1.974358  117.096035
...         ...      ...       ...         ...
116995  223.377  451.449  1.591080  294.398640
116996  223.885  450.748  1.591080  290.438050
116997  224.393  450.046  1.591080  286.477460
116998  224.901  449.344  1.591080  282.516870
116999  225.409  448.643  1.591080  278.556280

[117000 rows x 4 columns]


Testing Dataset:


         pos_x    pos_y  speed  energy
0      204.428  583.988    0.0     0.0
1      204.428  583.988    0.0     0.0
2      204.428  583.988    0.0     0.0
3      204.428  583.988    0.0     0.0
4      204.428  583.988    0.0     0.0
...        ...      ...    ...     ...
17995  210.673  468.992    0.0     0.0
17996  210.673  468.992    0.0     0.0
17997  210.673  468.992    0.0     0.0
17998  210.673  468.992    0.0     0.0
17999  210.673  468.992    0.0     0.0

[18000 rows x 4 columns]

X_data_training = all_data_training[0:-1]
X_data_training.reset_index(drop=True, inplace=True)

X_data_testing = all_data_testing[0:-1]
X_data_testing.reset_index(drop=True, inplace=True)

y_data_training = all_data_training[1:]
y_data_training.reset_index(drop=True, inplace=True)
y_data_training.columns = ["pos_x_result","pos_y_result","speed_result","energy_result"]

y_data_testing = all_data_testing[1:]
y_data_testing.reset_index(drop=True, inplace=True)
y_data_testing.columns = ["pos_x_result","pos_y_result","speed_result","energy_result"]

Split Dataset

X_training_data = X_data_training
X_testing_data = X_data_testing

y_training_data = y_data_training
y_testing_data = y_data_testing
y_training_data.reset_index(drop=True, inplace=True)
y_testing_data.reset_index(drop=True, inplace=True)

y_training_data_pos_x = y_training_data["pos_x_result"]
y_training_data_pos_y = y_training_data["pos_y_result"]
y_training_data_speed = y_training_data["speed_result"]
y_training_data_energy = y_training_data["energy_result"]

y_testing_data_pos_x = y_testing_data["pos_x_result"]
y_testing_data_pos_y = y_testing_data["pos_y_result"]
y_testing_data_speed = y_testing_data["speed_result"]
y_testing_data_energy = y_testing_data["energy_result"]

Scale Dataset

scaler=MinMaxScaler(feature_range=(0,1))
X_training_data_scale=scaler.fit_transform(np.array(X_training_data))
X_testing_data_scale=scaler.fit_transform(np.array(X_testing_data))
X_training_data_reshaped = X_training_data_scale.reshape(X_training_data_scale.shape[0],X_training_data_scale.shape[1] , 1)
X_testing_data_reshaped = X_testing_data_scale.reshape(X_testing_data_scale.shape[0],X_testing_data_scale.shape[1] , 1)

class timecallback1(tf.keras.callbacks.Callback):
    def __init__(self):
        self.times = []
        self.timetaken = time.process_time()

    def on_epoch_end(self,epoch,logs = {}):
        self.times.append((epoch,time.process_time() - self.timetaken))
    def on_train_end(self,logs = {}):
        plt.xlabel('Epochs')
        plt.ylabel('Time (seconds)')
        plt.plot(*zip(*self.times))
        plt.show()
        
class timecallback2(tf.keras.callbacks.Callback):
    def __init__(self):
        self.times = []
        self.timetaken = time.process_time()

    def on_epoch_end(self,epoch,logs = {}):
        self.times.append((epoch,time.process_time() - self.timetaken))
    def on_train_end(self,logs = {}):
        plt.xlabel('Epochs')
        plt.ylabel('Time (seconds)')
        plt.plot(*zip(*self.times))
        plt.show()
        
class timecallback3(tf.keras.callbacks.Callback):
    def __init__(self):
        self.times = []
        self.timetaken = time.process_time()

    def on_epoch_end(self,epoch,logs = {}):
        self.times.append((epoch,time.process_time() - self.timetaken))
    def on_train_end(self,logs = {}):
        plt.xlabel('Epochs')
        plt.ylabel('Time (seconds)')
        plt.plot(*zip(*self.times))
        plt.show()
        
class timecallback4(tf.keras.callbacks.Callback):
    def __init__(self):
        self.times = []
        self.timetaken = time.process_time()

    def on_epoch_end(self,epoch,logs = {}):
        self.times.append((epoch,time.process_time() - self.timetaken))
    def on_train_end(self,logs = {}):
        plt.xlabel('Epochs')
        plt.ylabel('Time (seconds)')
        plt.plot(*zip(*self.times))
        plt.show()
        

class timecallback5(tf.keras.callbacks.Callback):
    def __init__(self):
        self.times = []
        self.timetaken = time.process_time()

    def on_epoch_end(self,epoch,logs = {}):
        self.times.append((epoch,time.process_time() - self.timetaken))
    def on_train_end(self,logs = {}):
        plt.xlabel('Epochs')
        plt.ylabel('Time (seconds)')
        plt.plot(*zip(*self.times))
        plt.show()
        
class timecallback6(tf.keras.callbacks.Callback):
    def __init__(self):
        self.times = []
        self.timetaken = time.process_time()

    def on_epoch_end(self,epoch,logs = {}):
        self.times.append((epoch,time.process_time() - self.timetaken))
    def on_train_end(self,logs = {}):
        plt.xlabel('Epochs')
        plt.ylabel('Time (seconds)')
        plt.plot(*zip(*self.times))
        plt.show()
        
class timecallback7(tf.keras.callbacks.Callback):
    def __init__(self):
        self.times = []
        self.timetaken = time.process_time()

    def on_epoch_end(self,epoch,logs = {}):
        self.times.append((epoch,time.process_time() - self.timetaken))
    def on_train_end(self,logs = {}):
        plt.xlabel('Epochs')
        plt.ylabel('Time (seconds)')
        plt.plot(*zip(*self.times))
        plt.show()

def plottime(timetaken_pos_x,timetaken_pos_y,timetaken_speed,timetaken_energy):
    timetaken4 = []
    alist = []
    for i in range(len(timetaken_pos_x)):
        timetaken4.append(timetaken_pos_x[i][1])
        timetaken4.append(timetaken_pos_y[i][1])
        timetaken4.append(timetaken_speed[i][1])
        timetaken4.append(timetaken_energy[i][1])
        alist.append(timetaken4)
        timetaken4 = []
    return(alist)

===============================

Stacked LSTM

===============================

Stacked_LSTM_Model_pos_x = Sequential()
Stacked_LSTM_Model_pos_x.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_pos_x.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_pos_x.add(LSTM(50))
Stacked_LSTM_Model_pos_x.add(Dense(1))
Stacked_LSTM_Model_pos_x.compile(loss='mean_squared_error',optimizer='adam')

Stacked_LSTM_Model_pos_y=Sequential()
Stacked_LSTM_Model_pos_y.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_pos_y.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_pos_y.add(LSTM(50))
Stacked_LSTM_Model_pos_y.add(Dense(1))
Stacked_LSTM_Model_pos_y.compile(loss='mean_squared_error',optimizer='adam')

Stacked_LSTM_Model_speed=Sequential()
Stacked_LSTM_Model_speed.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_speed.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_speed.add(LSTM(50))
Stacked_LSTM_Model_speed.add(Dense(1))
Stacked_LSTM_Model_speed.compile(loss='mean_squared_error',optimizer='adam')

Stacked_LSTM_Model_energy=Sequential()
Stacked_LSTM_Model_energy.add(LSTM(50,return_sequences=True,input_shape=(4,1)))
Stacked_LSTM_Model_energy.add(LSTM(50,return_sequences=True))
Stacked_LSTM_Model_energy.add(LSTM(50))
Stacked_LSTM_Model_energy.add(Dense(1))
Stacked_LSTM_Model_energy.compile(loss='mean_squared_error',optimizer='adam')

timetaken_Stacked_LSTM_Model_pos_x = timecallback1()
timetaken_Stacked_LSTM_Model_pos_y = timecallback1()
timetaken_Stacked_LSTM_Model_speed = timecallback1()
timetaken_Stacked_LSTM_Model_energy = timecallback1()

Stacked_LSTM_Model_pos_x.fit(X_training_data_reshaped,y_training_data_pos_x,validation_data=(X_testing_data_reshaped,y_testing_data_pos_x),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_Stacked_LSTM_Model_pos_x])
Stacked_LSTM_Model_pos_y.fit(X_training_data_reshaped,y_training_data_pos_y,validation_data=(X_testing_data_reshaped,y_testing_data_pos_y),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_Stacked_LSTM_Model_pos_y])
Stacked_LSTM_Model_speed.fit(X_training_data_reshaped,y_training_data_speed,validation_data=(X_testing_data_reshaped,y_testing_data_speed),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_Stacked_LSTM_Model_speed])
Stacked_LSTM_Model_energy.fit(X_training_data_reshaped,y_training_data_energy,validation_data=(X_testing_data_reshaped,y_testing_data_energy),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_Stacked_LSTM_Model_energy])

Epoch 1/5
1829/1829 [==============================] - 27s 11ms/step - loss: 81570.2744 - val_loss: 51727.4961
Epoch 2/5
1829/1829 [==============================] - 18s 10ms/step - loss: 46146.9497 - val_loss: 30678.4590
Epoch 3/5
1829/1829 [==============================] - 18s 10ms/step - loss: 27360.9563 - val_loss: 15573.7168
Epoch 4/5
1829/1829 [==============================] - 18s 10ms/step - loss: 12983.8727 - val_loss: 7571.6685
Epoch 5/5
1829/1829 [==============================] - 18s 10ms/step - loss: 6068.0599 - val_loss: 3751.4653

Epoch 1/5
1829/1829 [==============================] - 26s 10ms/step - loss: 76215.4671 - val_loss: 49348.3672
Epoch 2/5
1829/1829 [==============================] - 16s 9ms/step - loss: 45051.4843 - val_loss: 32321.6895
Epoch 3/5
1829/1829 [==============================] - 16s 9ms/step - loss: 30387.5768 - val_loss: 26208.3691
Epoch 4/5
1829/1829 [==============================] - 17s 9ms/step - loss: 25396.4636 - val_loss: 25431.1543
Epoch 5/5
1829/1829 [==============================] - 18s 10ms/step - loss: 24731.4805 - val_loss: 25464.9824

Epoch 1/5
1829/1829 [==============================] - 31s 12ms/step - loss: 3.1066 - val_loss: 2.9942
Epoch 2/5
1829/1829 [==============================] - 23s 12ms/step - loss: 0.2317 - val_loss: 1.3367
Epoch 3/5
1829/1829 [==============================] - 17s 9ms/step - loss: 0.2397 - val_loss: 0.7172
Epoch 4/5
1829/1829 [==============================] - 16s 9ms/step - loss: 0.2206 - val_loss: 0.5188
Epoch 5/5
1829/1829 [==============================] - 17s 9ms/step - loss: 0.2311 - val_loss: 0.4419

Epoch 1/5
1829/1829 [==============================] - 29s 12ms/step - loss: 1497688.9598 - val_loss: 489989.0312
Epoch 2/5
1829/1829 [==============================] - 18s 10ms/step - loss: 1343236.6204 - val_loss: 428110.4062
Epoch 3/5
1829/1829 [==============================] - 18s 10ms/step - loss: 1189208.3846 - val_loss: 382611.5000
Epoch 4/5
1829/1829 [==============================] - 17s 10ms/step - loss: 1037805.2610 - val_loss: 352568.6875
Epoch 5/5
1829/1829 [==============================] - 19s 10ms/step - loss: 931407.6512 - val_loss: 337516.1875

<tensorflow.python.keras.callbacks.History at 0x1969d1c9580>

print("\n\n==================================================")
print("           TIME TAKEN BY STACKED LSTM               ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(10, 5)
plt.plot(plottime(timetaken_Stacked_LSTM_Model_pos_x.times,timetaken_Stacked_LSTM_Model_pos_y.times,timetaken_Stacked_LSTM_Model_speed.times,timetaken_Stacked_LSTM_Model_energy.times))
plt.title('TIME')
plt.legend(['POS X','POS Y', "SPEED", "ENERGY"], loc='upper left')
plt.xlabel('Epochs')
plt.ylabel('Time (seconds)')
plt.show()

==================================================
           TIME TAKEN BY STACKED LSTM               
==================================================

Predictions

train_predict_Stacked_LSTM_Model_pos_x = Stacked_LSTM_Model_pos_x.predict(X_training_data_reshaped)
test_predict_Stacked_LSTM_Model_pos_x = Stacked_LSTM_Model_pos_x.predict(X_testing_data_reshaped)

train_predict_Stacked_LSTM_Model_pos_y = Stacked_LSTM_Model_pos_y.predict(X_training_data_reshaped)
test_predict_Stacked_LSTM_Model_pos_y = Stacked_LSTM_Model_pos_y.predict(X_testing_data_reshaped)

train_predict_Stacked_LSTM_Model_speed = Stacked_LSTM_Model_speed.predict(X_training_data_reshaped)
test_predict_Stacked_LSTM_Model_speed = Stacked_LSTM_Model_speed.predict(X_testing_data_reshaped)

train_predict_Stacked_LSTM_Model_energy = Stacked_LSTM_Model_energy.predict(X_training_data_reshaped)
test_predict_Stacked_LSTM_Model_energy = Stacked_LSTM_Model_energy.predict(X_testing_data_reshaped)

print("\n\nPredictions Returned by Stacked LSTM: ")
print("=====================================\n\n")
df_prediction_Stacked_LSTM = pd.DataFrame()
df_prediction_Stacked_LSTM["Pos X Actual"] = y_testing_data_pos_x
df_prediction_Stacked_LSTM["Pos X Predicted"] = test_predict_Stacked_LSTM_Model_pos_x
df_prediction_Stacked_LSTM["Pos Y Actual"] = y_testing_data_pos_y
df_prediction_Stacked_LSTM["Pos Y Predicted"] = test_predict_Stacked_LSTM_Model_pos_y
df_prediction_Stacked_LSTM["Speed Actual"] = y_testing_data_speed
df_prediction_Stacked_LSTM["Speed Predicted"] = test_predict_Stacked_LSTM_Model_speed
df_prediction_Stacked_LSTM["Energy Actual"] = y_testing_data_energy
df_prediction_Stacked_LSTM["Energy Predicted"] = test_predict_Stacked_LSTM_Model_energy
print(df_prediction_Stacked_LSTM)

Predictions Returned by Stacked LSTM: 
=====================================


       Pos X Actual  Pos X Predicted  Pos Y Actual  Pos Y Predicted  \
0           204.428       209.718674       583.988       258.440094   
1           204.428       209.718674       583.988       258.440094   
2           204.428       209.718674       583.988       258.440094   
3           204.428       209.718674       583.988       258.440094   
4           204.428       209.718674       583.988       258.440094   
...             ...              ...           ...              ...   
17994       210.673       214.694153       468.992       258.440125   
17995       210.673       214.694153       468.992       258.440125   
17996       210.673       214.694153       468.992       258.440125   
17997       210.673       214.694153       468.992       258.440125   
17998       210.673       214.694153       468.992       258.440125   

       Speed Actual  Speed Predicted  Energy Actual  Energy Predicted  
0               0.0        -0.004185            0.0        451.944275  
1               0.0        -0.004185            0.0        451.944275  
2               0.0        -0.004185            0.0        451.944275  
3               0.0        -0.004185            0.0        451.944275  
4               0.0        -0.004185            0.0        451.944275  
...             ...              ...            ...               ...  
17994           0.0        -0.005373            0.0        451.944275  
17995           0.0        -0.005373            0.0        451.944275  
17996           0.0        -0.005373            0.0        451.944275  
17997           0.0        -0.005373            0.0        451.944275  
17998           0.0        -0.005373            0.0        451.944275  

[17999 rows x 8 columns]

RMSE

print("\n\nRMSE on Training Data by Stacked LSTM: ")
print("======================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x,train_predict_Stacked_LSTM_Model_pos_x)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y,train_predict_Stacked_LSTM_Model_pos_y)))
print(math.sqrt(mean_squared_error(y_training_data_speed,train_predict_Stacked_LSTM_Model_speed)))
print(math.sqrt(mean_squared_error(y_training_data_energy,train_predict_Stacked_LSTM_Model_energy)))

print("\n\nRMSE on Testing Data by Stacked LSTM: ")
print("=====================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_Stacked_LSTM_Model_pos_x)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_Stacked_LSTM_Model_pos_y)))
print(math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_Stacked_LSTM_Model_speed)))
print(math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_Stacked_LSTM_Model_energy)))

RMSE on Training Data by Stacked LSTM: 
======================================


58.37254251538838
157.34467053001828
0.4712893586006386
921.6971831440678


RMSE on Testing Data by Stacked LSTM: 
=====================================


61.24921169192751
159.57752386657987
0.6647372753997914
580.9612708079775

Graph

plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x)
plt.plot(test_predict_Stacked_LSTM_Model_pos_x)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y)
plt.plot(test_predict_Stacked_LSTM_Model_pos_y)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed)
plt.plot(test_predict_Stacked_LSTM_Model_speed)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy)
plt.plot(test_predict_Stacked_LSTM_Model_energy)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

===============================

CNN LSTM

===============================

X_training_data_reshaped_cnn = X_training_data_scale.reshape(X_training_data_scale.shape[0],1,X_training_data_scale.shape[1] , 1)
X_testing_data_reshaped_cnn = X_testing_data_scale.reshape(X_testing_data_scale.shape[0],1,X_testing_data_scale.shape[1] , 1)

CNN_LSTM_Model_pos_x = Sequential()
CNN_LSTM_Model_pos_x.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_pos_x.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_pos_x.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_pos_x.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_pos_x.add(Dense(1))
CNN_LSTM_Model_pos_x.compile(loss='mean_squared_error',optimizer='adam')

CNN_LSTM_Model_pos_y = Sequential()
CNN_LSTM_Model_pos_y.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_pos_y.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_pos_y.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_pos_y.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_pos_y.add(Dense(1))
CNN_LSTM_Model_pos_y.compile(loss='mean_squared_error',optimizer='adam')

CNN_LSTM_Model_speed = Sequential()
CNN_LSTM_Model_speed.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_speed.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_speed.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_speed.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_speed.add(Dense(1))
CNN_LSTM_Model_speed.compile(loss='mean_squared_error',optimizer='adam')

CNN_LSTM_Model_energy = Sequential()
CNN_LSTM_Model_energy.add(TimeDistributed(Conv1D(filters=64, kernel_size=1, activation='relu'), input_shape=(None, 4, 1)))
CNN_LSTM_Model_energy.add(TimeDistributed(MaxPooling1D(pool_size=2)))
CNN_LSTM_Model_energy.add(TimeDistributed(Flatten()))
CNN_LSTM_Model_energy.add(LSTM(50, activation='relu'))
CNN_LSTM_Model_energy.add(Dense(1))
CNN_LSTM_Model_energy.compile(loss='mean_squared_error',optimizer='adam')

timetaken_CNN_LSTM_Model_pos_x = timecallback2()
timetaken_CNN_LSTM_Model_pos_y = timecallback2()
timetaken_CNN_LSTM_Model_speed = timecallback2()
timetaken_CNN_LSTM_Model_energy = timecallback2()

CNN_LSTM_Model_pos_x.fit(X_training_data_reshaped_cnn,y_training_data_pos_x,validation_data=(X_testing_data_reshaped_cnn,y_testing_data_pos_x),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_CNN_LSTM_Model_pos_x])
CNN_LSTM_Model_pos_y.fit(X_training_data_reshaped_cnn,y_training_data_pos_y,validation_data=(X_testing_data_reshaped_cnn,y_testing_data_pos_y),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_CNN_LSTM_Model_pos_y])
CNN_LSTM_Model_speed.fit(X_training_data_reshaped_cnn,y_training_data_speed,validation_data=(X_testing_data_reshaped_cnn,y_testing_data_speed),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_CNN_LSTM_Model_speed])
CNN_LSTM_Model_energy.fit(X_training_data_reshaped_cnn,y_training_data_energy,validation_data=(X_testing_data_reshaped_cnn,y_testing_data_energy),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_CNN_LSTM_Model_energy])

Epoch 1/5
1829/1829 [==============================] - 7s 3ms/step - loss: 38908.5114 - val_loss: 10747.5811
Epoch 2/5
1829/1829 [==============================] - 5s 3ms/step - loss: 10184.3334 - val_loss: 10540.9326
Epoch 3/5
1829/1829 [==============================] - 5s 3ms/step - loss: 10120.0360 - val_loss: 10530.2949
Epoch 4/5
1829/1829 [==============================] - 5s 3ms/step - loss: 10099.8749 - val_loss: 10533.6064
Epoch 5/5
1829/1829 [==============================] - 5s 3ms/step - loss: 9893.1339 - val_loss: 10438.9150

Epoch 1/5
   1/1829 [..............................] - ETA: 53:26 - loss: 98367.8359WARNING:tensorflow:Callback method `on_train_batch_end` is slow compared to the batch time (batch time: 0.0018s vs `on_train_batch_end` time: 0.0031s). Check your callbacks.
1829/1829 [==============================] - 7s 3ms/step - loss: 42879.4923 - val_loss: 17516.8184
Epoch 2/5
1829/1829 [==============================] - 5s 3ms/step - loss: 15855.3817 - val_loss: 17161.2402
Epoch 3/5
1829/1829 [==============================] - 6s 3ms/step - loss: 15510.2799 - val_loss: 17403.1953
Epoch 4/5
1829/1829 [==============================] - 6s 3ms/step - loss: 15424.0000 - val_loss: 17432.6191
Epoch 5/5
1829/1829 [==============================] - 5s 3ms/step - loss: 15432.0166 - val_loss: 17807.0840

Epoch 1/5
1829/1829 [==============================] - 7s 3ms/step - loss: 2.8771 - val_loss: 1.3213
Epoch 2/5
1829/1829 [==============================] - 5s 3ms/step - loss: 0.2081 - val_loss: 1.3475
Epoch 3/5
1829/1829 [==============================] - 5s 3ms/step - loss: 0.2301 - val_loss: 1.2994
Epoch 4/5
1829/1829 [==============================] - 5s 3ms/step - loss: 0.2070 - val_loss: 1.2630
Epoch 5/5
1829/1829 [==============================] - 5s 3ms/step - loss: 0.2228 - val_loss: 1.2825

Epoch 1/5
1829/1829 [==============================] - 7s 3ms/step - loss: 982434.8077 - val_loss: 491352.3438
Epoch 2/5
1829/1829 [==============================] - 5s 3ms/step - loss: 536544.3404 - val_loss: 499125.5625
Epoch 3/5
1829/1829 [==============================] - 5s 3ms/step - loss: 530912.0473 - val_loss: 515408.1250
Epoch 4/5
1829/1829 [==============================] - 5s 3ms/step - loss: 533769.1806 - val_loss: 492322.4688
Epoch 5/5
1829/1829 [==============================] - 5s 3ms/step - loss: 542602.5698 - val_loss: 476677.8438

<tensorflow.python.keras.callbacks.History at 0x196b6e7f550>

print("\n\n==================================================")
print("           TIME TAKEN BY CNN LSTM               ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(10, 5)
plt.plot(plottime(timetaken_CNN_LSTM_Model_pos_x.times,timetaken_CNN_LSTM_Model_pos_y.times,timetaken_CNN_LSTM_Model_speed.times,timetaken_CNN_LSTM_Model_energy.times))
plt.title('TIME')
plt.legend(['POS X','POS Y', "SPEED", "ENERGY"], loc='upper left')
plt.xlabel('Epochs')
plt.ylabel('Time (seconds)')
plt.show()

==================================================
           TIME TAKEN BY CNN LSTM               
==================================================

Predictions

train_predict_CNN_LSTM_Model_pos_x = CNN_LSTM_Model_pos_x.predict(X_training_data_reshaped_cnn)
test_predict_CNN_LSTM_Model_pos_x = CNN_LSTM_Model_pos_x.predict(X_testing_data_reshaped_cnn)

train_predict_CNN_LSTM_Model_pos_y = CNN_LSTM_Model_pos_y.predict(X_training_data_reshaped_cnn)
test_predict_CNN_LSTM_Model_pos_y = CNN_LSTM_Model_pos_y.predict(X_testing_data_reshaped_cnn)

train_predict_CNN_LSTM_Model_speed = CNN_LSTM_Model_speed.predict(X_training_data_reshaped_cnn)
test_predict_CNN_LSTM_Model_speed = CNN_LSTM_Model_speed.predict(X_testing_data_reshaped_cnn)

train_predict_CNN_LSTM_Model_energy = CNN_LSTM_Model_energy.predict(X_training_data_reshaped_cnn)
test_predict_CNN_LSTM_Model_energy = CNN_LSTM_Model_energy.predict(X_testing_data_reshaped_cnn)

print("\n\nPredictions Returned by CNN LSTM: ")
print("=================================\n\n")
df_prediction_CNN_LSTM = pd.DataFrame()
df_prediction_CNN_LSTM["Pos X Actual"] = y_testing_data_pos_x
df_prediction_CNN_LSTM["Pos X Predicted"] = test_predict_CNN_LSTM_Model_pos_x
df_prediction_CNN_LSTM["Pos Y Actual"] = y_testing_data_pos_y
df_prediction_CNN_LSTM["Pos Y Predicted"] = test_predict_CNN_LSTM_Model_pos_y
df_prediction_CNN_LSTM["Speed Actual"] = y_testing_data_speed
df_prediction_CNN_LSTM["Speed Predicted"] = test_predict_CNN_LSTM_Model_speed
df_prediction_CNN_LSTM["Energy Actual"] = y_testing_data_energy
df_prediction_CNN_LSTM["Energy Predicted"] = test_predict_CNN_LSTM_Model_energy
print(df_prediction_CNN_LSTM)

Predictions Returned by CNN LSTM: 
=================================


       Pos X Actual  Pos X Predicted  Pos Y Actual  Pos Y Predicted  \
0           204.428       402.461395       583.988       528.332214   
1           204.428       402.461395       583.988       528.332214   
2           204.428       402.461395       583.988       528.332214   
3           204.428       402.461395       583.988       528.332214   
4           204.428       402.461395       583.988       528.332214   
...             ...              ...           ...              ...   
17994       210.673       340.185272       468.992       412.224121   
17995       210.673       340.185272       468.992       412.224121   
17996       210.673       340.185272       468.992       412.224121   
17997       210.673       340.185272       468.992       412.224121   
17998       210.673       340.185272       468.992       412.224121   

       Speed Actual  Speed Predicted  Energy Actual  Energy Predicted  
0               0.0         0.020494            0.0        819.862000  
1               0.0         0.020494            0.0        819.862000  
2               0.0         0.020494            0.0        819.862000  
3               0.0         0.020494            0.0        819.862000  
4               0.0         0.020494            0.0        819.862000  
...             ...              ...            ...               ...  
17994           0.0         0.024752            0.0        803.092529  
17995           0.0         0.024752            0.0        803.092529  
17996           0.0         0.024752            0.0        803.092529  
17997           0.0         0.024752            0.0        803.092529  
17998           0.0         0.024752            0.0        803.092529  

[17999 rows x 8 columns]

RMSE

print("\n\nRMSE on Training Data by CNN LSTM: ")
print("==================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x,train_predict_CNN_LSTM_Model_pos_x)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y,train_predict_CNN_LSTM_Model_pos_y)))
print(math.sqrt(mean_squared_error(y_training_data_speed,train_predict_CNN_LSTM_Model_speed)))
print(math.sqrt(mean_squared_error(y_training_data_energy,train_predict_CNN_LSTM_Model_energy)))

print("\n\nRMSE on Testing Data by CNN LSTM: ")
print("==================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_CNN_LSTM_Model_pos_x)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_CNN_LSTM_Model_pos_y)))
print(math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_CNN_LSTM_Model_speed)))
print(math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_CNN_LSTM_Model_energy)))

RMSE on Training Data by CNN LSTM: 
==================================


99.8678195852092
124.6874789630821
0.45566232479038715
731.2833863598536


RMSE on Testing Data by CNN LSTM: 
==================================


102.1710234948836
133.44322081508946
1.1324576016620895
690.4185139473112

Graph

plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x)
plt.plot(test_predict_CNN_LSTM_Model_pos_x)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y)
plt.plot(test_predict_CNN_LSTM_Model_pos_y)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')

plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed)
plt.plot(test_predict_CNN_LSTM_Model_speed)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy)
plt.plot(test_predict_CNN_LSTM_Model_energy)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

===============================

LSTM

===============================

LSTM_Model_pos_x = Sequential()
LSTM_Model_pos_x.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_pos_x.add(Dense(1))
LSTM_Model_pos_x.compile(loss='mean_squared_error',optimizer='adam')

LSTM_Model_pos_y = Sequential()
LSTM_Model_pos_y.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_pos_y.add(Dense(1))
LSTM_Model_pos_y.compile(loss='mean_squared_error',optimizer='adam')

LSTM_Model_speed = Sequential()
LSTM_Model_speed.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_speed.add(Dense(1))
LSTM_Model_speed.compile(loss='mean_squared_error',optimizer='adam')

LSTM_Model_energy = Sequential()
LSTM_Model_energy.add(LSTM(50,input_shape=(4,1)))
LSTM_Model_energy.add(Dense(1))
LSTM_Model_energy.compile(loss='mean_squared_error',optimizer='adam')

timetaken_LSTM_Model_pos_x = timecallback3()
timetaken_LSTM_Model_pos_y = timecallback3()
timetaken_LSTM_Model_speed = timecallback3()
timetaken_LSTM_Model_energy = timecallback3()

LSTM_Model_pos_x.fit(X_training_data_reshaped,y_training_data_pos_x,validation_data=(X_testing_data_reshaped,y_testing_data_pos_x),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_LSTM_Model_pos_x])
LSTM_Model_pos_y.fit(X_training_data_reshaped,y_training_data_pos_y,validation_data=(X_testing_data_reshaped,y_testing_data_pos_y),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_LSTM_Model_pos_y])
LSTM_Model_speed.fit(X_training_data_reshaped,y_training_data_speed,validation_data=(X_testing_data_reshaped,y_testing_data_speed),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_LSTM_Model_speed])
LSTM_Model_energy.fit(X_training_data_reshaped,y_training_data_energy,validation_data=(X_testing_data_reshaped,y_testing_data_energy),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_LSTM_Model_energy])

Epoch 1/5
1829/1829 [==============================] - 10s 4ms/step - loss: 81832.0552 - val_loss: 50810.2930
Epoch 2/5
1829/1829 [==============================] - 7s 4ms/step - loss: 44973.3411 - val_loss: 30087.6699
Epoch 3/5
1829/1829 [==============================] - 7s 4ms/step - loss: 27178.1999 - val_loss: 21435.4453
Epoch 4/5
1829/1829 [==============================] - 8s 4ms/step - loss: 18436.4360 - val_loss: 8218.7969
Epoch 5/5
1829/1829 [==============================] - 7s 4ms/step - loss: 6584.8776 - val_loss: 3851.5674

Epoch 1/5
1829/1829 [==============================] - 10s 4ms/step - loss: 75999.9022 - val_loss: 48443.2539
Epoch 2/5
1829/1829 [==============================] - 7s 4ms/step - loss: 44144.8976 - val_loss: 31831.8848
Epoch 3/5
1829/1829 [==============================] - 7s 4ms/step - loss: 30023.7598 - val_loss: 26108.3887
Epoch 4/5
1829/1829 [==============================] - 7s 4ms/step - loss: 25408.2239 - val_loss: 25432.1211
Epoch 5/5
1829/1829 [==============================] - 7s 4ms/step - loss: 22799.6204 - val_loss: 8290.9033

Epoch 1/5
1829/1829 [==============================] - 10s 4ms/step - loss: 3.2661 - val_loss: 0.4206
Epoch 2/5
1829/1829 [==============================] - 7s 4ms/step - loss: 0.2270 - val_loss: 0.4716
Epoch 3/5
1829/1829 [==============================] - 7s 4ms/step - loss: 0.2188 - val_loss: 0.4448
Epoch 4/5
1829/1829 [==============================] - 7s 4ms/step - loss: 0.2288 - val_loss: 0.4051
Epoch 5/5
1829/1829 [==============================] - 7s 4ms/step - loss: 0.2120 - val_loss: 0.3906

Epoch 1/5
1829/1829 [==============================] - 10s 4ms/step - loss: 1486240.5685 - val_loss: 488824.0000
Epoch 2/5
1829/1829 [==============================] - 7s 4ms/step - loss: 1314580.7353 - val_loss: 426992.8125
Epoch 3/5
1829/1829 [==============================] - 7s 4ms/step - loss: 1153391.8596 - val_loss: 381654.6875
Epoch 4/5
1829/1829 [==============================] - 7s 4ms/step - loss: 1046974.2002 - val_loss: 352002.4062
Epoch 5/5
1829/1829 [==============================] - 7s 4ms/step - loss: 911440.3258 - val_loss: 337320.9688

<tensorflow.python.keras.callbacks.History at 0x196c954fa90>

print("\n\n==================================================")
print("           TIME TAKEN BY LSTM               ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(10, 5)
plt.plot(plottime(timetaken_LSTM_Model_pos_x.times,timetaken_LSTM_Model_pos_y.times,timetaken_LSTM_Model_speed.times,timetaken_LSTM_Model_energy.times))
plt.title('TIME')
plt.legend(['POS X','POS Y', "SPEED", "ENERGY"], loc='upper left')
plt.xlabel('Epochs')
plt.ylabel('Time (seconds)')
plt.show()

==================================================
           TIME TAKEN BY LSTM               
==================================================

Predictions

train_predict_LSTM_Model_pos_x = LSTM_Model_pos_x.predict(X_training_data_reshaped)
test_predict_LSTM_Model_pos_x = LSTM_Model_pos_x.predict(X_testing_data_reshaped)

train_predict_LSTM_Model_pos_y = LSTM_Model_pos_y.predict(X_training_data_reshaped)
test_predict_LSTM_Model_pos_y = LSTM_Model_pos_y.predict(X_testing_data_reshaped)

train_predict_LSTM_Model_speed = LSTM_Model_speed.predict(X_training_data_reshaped)
test_predict_LSTM_Model_speed = LSTM_Model_speed.predict(X_testing_data_reshaped)

train_predict_LSTM_Model_energy = LSTM_Model_energy.predict(X_training_data_reshaped)
test_predict_LSTM_Model_energy = LSTM_Model_energy.predict(X_testing_data_reshaped)

print("\n\nPredictions Returned by LSTM: ")
print("=============================\n\n")
df_prediction_LSTM = pd.DataFrame()
df_prediction_LSTM["Pos X Actual"] = y_testing_data_pos_x
df_prediction_LSTM["Pos X Predicted"] = test_predict_LSTM_Model_pos_x
df_prediction_LSTM["Pos Y Actual"] = y_testing_data_pos_y
df_prediction_LSTM["Pos Y Predicted"] = test_predict_LSTM_Model_pos_y
df_prediction_LSTM["Speed Actual"] = y_testing_data_speed
df_prediction_LSTM["Speed Predicted"] = test_predict_LSTM_Model_speed
df_prediction_LSTM["Energy Actual"] = y_testing_data_energy
df_prediction_LSTM["Energy Predicted"] = test_predict_LSTM_Model_energy
print(df_prediction_LSTM)

Predictions Returned by LSTM: 
=============================


       Pos X Actual  Pos X Predicted  Pos Y Actual  Pos Y Predicted  \
0           204.428       201.097336       583.988       321.968933   
1           204.428       201.097336       583.988       321.968933   
2           204.428       201.097336       583.988       321.968933   
3           204.428       201.097336       583.988       321.968933   
4           204.428       201.097336       583.988       321.968933   
...             ...              ...           ...              ...   
17994       210.673       203.813965       468.992       321.278107   
17995       210.673       203.813965       468.992       321.278107   
17996       210.673       203.813965       468.992       321.278107   
17997       210.673       203.813965       468.992       321.278107   
17998       210.673       203.813965       468.992       321.278107   

       Speed Actual  Speed Predicted  Energy Actual  Energy Predicted  
0               0.0        -0.110139            0.0        454.125641  
1               0.0        -0.110139            0.0        454.125641  
2               0.0        -0.110139            0.0        454.125641  
3               0.0        -0.110139            0.0        454.125641  
4               0.0        -0.110139            0.0        454.125641  
...             ...              ...            ...               ...  
17994           0.0        -0.125710            0.0        454.126526  
17995           0.0        -0.125710            0.0        454.126526  
17996           0.0        -0.125711            0.0        454.126526  
17997           0.0        -0.125711            0.0        454.126526  
17998           0.0        -0.125711            0.0        454.126526  

[17999 rows x 8 columns]

RMSE

print("\n\nRMSE on Training Data by LSTM: ")
print("==============================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x,train_predict_LSTM_Model_pos_x)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y,train_predict_LSTM_Model_pos_y)))
print(math.sqrt(mean_squared_error(y_training_data_speed,train_predict_LSTM_Model_speed)))
print(math.sqrt(mean_squared_error(y_training_data_energy,train_predict_LSTM_Model_energy)))

print("\n\nRMSE on Training Data by LSTM: ")
print("=============================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_LSTM_Model_pos_x)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_LSTM_Model_pos_y)))
print(math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_LSTM_Model_speed)))
print(math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_LSTM_Model_energy)))

RMSE on Training Data by LSTM: 
==============================


59.17666556839156
89.15748689711326
0.4730585962760645
920.4088801303808


RMSE on Training Data by LSTM: 
=============================


62.06099552130979
91.05439630731244
0.6249464855007287
580.793525264608

Graph

plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x)
plt.plot(test_predict_LSTM_Model_pos_x)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y)
plt.plot(test_predict_LSTM_Model_pos_y)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed)
plt.plot(test_predict_LSTM_Model_speed)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy)
plt.plot(test_predict_LSTM_Model_energy)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

===============================

Bi-Directional LSTM

===============================

BiDirectonal_LSTM_Model_pos_x = Sequential()
BiDirectonal_LSTM_Model_pos_x.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_pos_x.add(Dense(1))
BiDirectonal_LSTM_Model_pos_x.compile(loss='mean_squared_error',optimizer='adam')

BiDirectonal_LSTM_Model_pos_y = Sequential()
BiDirectonal_LSTM_Model_pos_y.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_pos_y.add(Dense(1))
BiDirectonal_LSTM_Model_pos_y.compile(loss='mean_squared_error',optimizer='adam')

BiDirectonal_LSTM_Model_speed = Sequential()
BiDirectonal_LSTM_Model_speed.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_speed.add(Dense(1))
BiDirectonal_LSTM_Model_speed.compile(loss='mean_squared_error',optimizer='adam')

BiDirectonal_LSTM_Model_energy = Sequential()
BiDirectonal_LSTM_Model_energy.add(Bidirectional(LSTM(50, activation='relu'), input_shape=(4, 1)))
BiDirectonal_LSTM_Model_energy.add(Dense(1))
BiDirectonal_LSTM_Model_energy.compile(loss='mean_squared_error',optimizer='adam')

timetaken_BiDirectonal_LSTM_Model_pos_x = timecallback4()
timetaken_BiDirectonal_LSTM_Model_pos_y = timecallback4()
timetaken_BiDirectonal_LSTM_Model_speed = timecallback4()
timetaken_BiDirectonal_LSTM_Model_energy = timecallback4()

BiDirectonal_LSTM_Model_pos_x.fit(X_training_data_reshaped,y_training_data_pos_x,validation_data=(X_testing_data_reshaped,y_testing_data_pos_x),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_BiDirectonal_LSTM_Model_pos_x])
BiDirectonal_LSTM_Model_pos_y.fit(X_training_data_reshaped,y_training_data_pos_y,validation_data=(X_testing_data_reshaped,y_testing_data_pos_y),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_BiDirectonal_LSTM_Model_pos_y])
BiDirectonal_LSTM_Model_speed.fit(X_training_data_reshaped,y_training_data_speed,validation_data=(X_testing_data_reshaped,y_testing_data_speed),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_BiDirectonal_LSTM_Model_speed])
BiDirectonal_LSTM_Model_energy.fit(X_training_data_reshaped,y_training_data_energy,validation_data=(X_testing_data_reshaped,y_testing_data_energy),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_BiDirectonal_LSTM_Model_energy])

Epoch 1/5
1829/1829 [==============================] - 11s 4ms/step - loss: 22502.4335 - val_loss: 504.2557
Epoch 2/5
1829/1829 [==============================] - 8s 4ms/step - loss: 150.9394 - val_loss: 497.6754
Epoch 3/5
1829/1829 [==============================] - 8s 4ms/step - loss: 137.6934 - val_loss: 469.9681
Epoch 4/5
1829/1829 [==============================] - 8s 4ms/step - loss: 150.4266 - val_loss: 454.0327
Epoch 5/5
1829/1829 [==============================] - 8s 4ms/step - loss: 150.6220 - val_loss: 453.9475

Epoch 1/5
1829/1829 [==============================] - 12s 5ms/step - loss: 32720.8197 - val_loss: 1809.1536
Epoch 2/5
1829/1829 [==============================] - 8s 4ms/step - loss: 190.8820 - val_loss: 1088.5913
Epoch 3/5
1829/1829 [==============================] - 8s 4ms/step - loss: 160.0131 - val_loss: 867.3106
Epoch 4/5
1829/1829 [==============================] - 8s 4ms/step - loss: 172.4966 - val_loss: 806.2817
Epoch 5/5
1829/1829 [==============================] - 8s 4ms/step - loss: 177.8866 - val_loss: 807.4897

Epoch 1/5
1829/1829 [==============================] - 12s 5ms/step - loss: 3.0185 - val_loss: 21.6616
Epoch 2/5
1829/1829 [==============================] - 8s 4ms/step - loss: 0.2423 - val_loss: 14.8800
Epoch 3/5
1829/1829 [==============================] - 8s 4ms/step - loss: 0.2162 - val_loss: 11.9025
Epoch 4/5
1829/1829 [==============================] - 8s 4ms/step - loss: 0.2307 - val_loss: 14.2430
Epoch 5/5
1829/1829 [==============================] - 8s 4ms/step - loss: 0.2202 - val_loss: 12.1735

Epoch 1/5
1829/1829 [==============================] - 11s 5ms/step - loss: 708645.3189 - val_loss: 35310928.0000
Epoch 2/5
1829/1829 [==============================] - 8s 4ms/step - loss: 44596.7841 - val_loss: 25439260.0000
Epoch 3/5
1829/1829 [==============================] - 8s 4ms/step - loss: 18256.8087 - val_loss: 17960876.0000
Epoch 4/5
1829/1829 [==============================] - 8s 4ms/step - loss: 15237.3524 - val_loss: 15995368.0000
Epoch 5/5
1829/1829 [==============================] - 8s 4ms/step - loss: 9883.4051 - val_loss: 16157761.0000

<tensorflow.python.keras.callbacks.History at 0x196de45a280>

print("\n\n==================================================")
print("           TIME TAKEN BY BiDirectonal LSTM               ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(10, 5)
plt.plot(plottime(timetaken_BiDirectonal_LSTM_Model_pos_x.times,timetaken_BiDirectonal_LSTM_Model_pos_y.times,timetaken_BiDirectonal_LSTM_Model_speed.times,timetaken_BiDirectonal_LSTM_Model_energy.times))
plt.title('TIME')
plt.legend(['POS X','POS Y', "SPEED", "ENERGY"], loc='upper left')
plt.xlabel('Epochs')
plt.ylabel('Time (seconds)')
plt.show()

==================================================
           TIME TAKEN BY BiDirectonal LSTM               
==================================================

Predictions

train_predict_BiDirectonal_LSTM_Model_pos_x = BiDirectonal_LSTM_Model_pos_x.predict(X_training_data_reshaped)
test_predict_BiDirectonal_LSTM_Model_pos_x = BiDirectonal_LSTM_Model_pos_x.predict(X_testing_data_reshaped)

train_predict_BiDirectonal_LSTM_Model_pos_y = BiDirectonal_LSTM_Model_pos_y.predict(X_training_data_reshaped)
test_predict_BiDirectonal_LSTM_Model_pos_y = BiDirectonal_LSTM_Model_pos_y.predict(X_testing_data_reshaped)

train_predict_BiDirectonal_LSTM_Model_speed = BiDirectonal_LSTM_Model_speed.predict(X_training_data_reshaped)
test_predict_BiDirectonal_LSTM_Model_speed = BiDirectonal_LSTM_Model_speed.predict(X_testing_data_reshaped)

train_predict_BiDirectonal_LSTM_Model_energy = BiDirectonal_LSTM_Model_energy.predict(X_training_data_reshaped)
test_predict_BiDirectonal_LSTM_Model_energy = BiDirectonal_LSTM_Model_energy.predict(X_testing_data_reshaped)

print("\n\nPredictions Returned by Bi-Directional LSTM: ")
print("=========================================\n\n")
df_prediction_BiDirectonal_LSTM = pd.DataFrame()
df_prediction_BiDirectonal_LSTM["Pos X Actual"] = y_testing_data_pos_x
df_prediction_BiDirectonal_LSTM["Pos X Predicted"] = test_predict_BiDirectonal_LSTM_Model_pos_x
df_prediction_BiDirectonal_LSTM["Pos Y Actual"] = y_testing_data_pos_y
df_prediction_BiDirectonal_LSTM["Pos Y Predicted"] = test_predict_BiDirectonal_LSTM_Model_pos_y
df_prediction_BiDirectonal_LSTM["Speed Actual"] = y_testing_data_speed
df_prediction_BiDirectonal_LSTM["Speed Predicted"] = test_predict_BiDirectonal_LSTM_Model_speed
df_prediction_BiDirectonal_LSTM["Energy Actual"] = y_testing_data_energy
df_prediction_BiDirectonal_LSTM["Energy Predicted"] = test_predict_BiDirectonal_LSTM_Model_energy
print(df_prediction_BiDirectonal_LSTM)

Predictions Returned by Bi-Directional LSTM: 
=========================================


       Pos X Actual  Pos X Predicted  Pos Y Actual  Pos Y Predicted  \
0           204.428       204.295532       583.988       584.744995   
1           204.428       204.295532       583.988       584.744995   
2           204.428       204.295532       583.988       584.744995   
3           204.428       204.295532       583.988       584.744995   
4           204.428       204.295532       583.988       584.744995   
...             ...              ...           ...              ...   
17994       210.673       210.206818       468.992       475.150757   
17995       210.673       210.206818       468.992       475.150757   
17996       210.673       210.206833       468.992       475.150696   
17997       210.673       210.206833       468.992       475.150696   
17998       210.673       210.206818       468.992       475.150696   

       Speed Actual  Speed Predicted  Energy Actual  Energy Predicted  
0               0.0         0.009640            0.0         10.052322  
1               0.0         0.009640            0.0         10.052322  
2               0.0         0.009640            0.0         10.052322  
3               0.0         0.009640            0.0         10.052322  
4               0.0         0.009640            0.0         10.052322  
...             ...              ...            ...               ...  
17994           0.0         0.093102            0.0          7.178122  
17995           0.0         0.093102            0.0          7.178122  
17996           0.0         0.093102            0.0          7.178174  
17997           0.0         0.093102            0.0          7.178174  
17998           0.0         0.093102            0.0          7.178174  

[17999 rows x 8 columns]

RMSE

print("\n\nRMSE on Training Data by Bi-Directonal LSTM: ")
print("===========================================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x,train_predict_BiDirectonal_LSTM_Model_pos_x)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y,train_predict_BiDirectonal_LSTM_Model_pos_y)))
print(math.sqrt(mean_squared_error(y_training_data_speed,train_predict_BiDirectonal_LSTM_Model_speed)))
print(math.sqrt(mean_squared_error(y_training_data_energy,train_predict_BiDirectonal_LSTM_Model_energy)))

print("\n\nRMSE on Testing Data by Bi-Directonal LSTM: ")
print("==========================================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_BiDirectonal_LSTM_Model_pos_x)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_BiDirectonal_LSTM_Model_pos_y)))
print(math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_BiDirectonal_LSTM_Model_speed)))
print(math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_BiDirectonal_LSTM_Model_energy)))

RMSE on Training Data by Bi-Directonal LSTM: 
===========================================


11.882069477647343
13.883404372335377
0.4602942135431375
101.77404298157245


RMSE on Testing Data by Bi-Directonal LSTM: 
==========================================


21.30604485598056
28.416358116269265
3.4890517432098926
4019.671459870819

Graph

plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_x)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_y)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed)
plt.plot(test_predict_BiDirectonal_LSTM_Model_speed)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy)
plt.plot(test_predict_BiDirectonal_LSTM_Model_energy)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

===============================

GRU

===============================

GRU_Model_pos_x = Sequential()
GRU_Model_pos_x.add(GRU(50,input_shape=(4,1)))
GRU_Model_pos_x.add(Dense(1000))
GRU_Model_pos_x.add(Dense(1))
GRU_Model_pos_x.compile(loss='mean_squared_error',optimizer='adam')

GRU_Model_pos_y = Sequential()
GRU_Model_pos_y.add(GRU(50,input_shape=(4,1)))
GRU_Model_pos_y.add(Dense(1000))
GRU_Model_pos_y.add(Dense(1))
GRU_Model_pos_y.compile(loss='mean_squared_error',optimizer='adam')

GRU_Model_speed = Sequential()
GRU_Model_speed.add(GRU(50,input_shape=(4,1)))
GRU_Model_speed.add(Dense(1000))
GRU_Model_speed.add(Dense(1))
GRU_Model_speed.compile(loss='mean_squared_error',optimizer='adam')

GRU_Model_energy = Sequential()
GRU_Model_energy.add(GRU(50,input_shape=(4,1)))
GRU_Model_energy.add(Dense(1000))
GRU_Model_energy.add(Dense(1))
GRU_Model_energy.compile(loss='mean_squared_error',optimizer='adam')

timetaken_GRU_Model_pos_x = timecallback5()
timetaken_GRU_Model_pos_y = timecallback5()
timetaken_GRU_Model_speed = timecallback5()
timetaken_GRU_Model_energy = timecallback5()

GRU_Model_pos_x.fit(X_training_data_reshaped,y_training_data_pos_x,validation_data=(X_testing_data_reshaped,y_testing_data_pos_x),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_GRU_Model_pos_x])
GRU_Model_pos_y.fit(X_training_data_reshaped,y_training_data_pos_y,validation_data=(X_testing_data_reshaped,y_testing_data_pos_y),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_GRU_Model_pos_y])
GRU_Model_speed.fit(X_training_data_reshaped,y_training_data_speed,validation_data=(X_testing_data_reshaped,y_testing_data_speed),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_GRU_Model_speed])
GRU_Model_energy.fit(X_training_data_reshaped,y_training_data_energy,validation_data=(X_testing_data_reshaped,y_testing_data_energy),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_GRU_Model_energy])

Epoch 1/5
1829/1829 [==============================] - 12s 5ms/step - loss: 15292.4894 - val_loss: 526.8732
Epoch 2/5
1829/1829 [==============================] - 9s 5ms/step - loss: 289.1758 - val_loss: 465.9839
Epoch 3/5
1829/1829 [==============================] - 8s 4ms/step - loss: 191.3046 - val_loss: 440.7192
Epoch 4/5
1829/1829 [==============================] - 8s 4ms/step - loss: 196.4775 - val_loss: 451.9869
Epoch 5/5
1829/1829 [==============================] - 9s 5ms/step - loss: 157.2557 - val_loss: 431.3060

Epoch 1/5
1829/1829 [==============================] - 29s 5ms/step - loss: 20204.5003 - val_loss: 878.0785
Epoch 2/5
1829/1829 [==============================] - 8s 4ms/step - loss: 227.9095 - val_loss: 704.0936
Epoch 3/5
1829/1829 [==============================] - 8s 4ms/step - loss: 200.6495 - val_loss: 806.3679
Epoch 4/5
1829/1829 [==============================] - 8s 4ms/step - loss: 178.0849 - val_loss: 558.7333
Epoch 5/5
1829/1829 [==============================] - 8s 5ms/step - loss: 160.4421 - val_loss: 545.3433

Epoch 1/5
1829/1829 [==============================] - 11s 5ms/step - loss: 1.3155 - val_loss: 0.6130
Epoch 2/5
1829/1829 [==============================] - 8s 4ms/step - loss: 0.2040 - val_loss: 0.4967
Epoch 3/5
1829/1829 [==============================] - 8s 4ms/step - loss: 0.2269 - val_loss: 0.4729
Epoch 4/5
1829/1829 [==============================] - 9s 5ms/step - loss: 0.2238 - val_loss: 0.4764
Epoch 5/5
1829/1829 [==============================] - 8s 5ms/step - loss: 0.2221 - val_loss: 0.4073

Epoch 1/5
1829/1829 [==============================] - 11s 5ms/step - loss: 688671.5324 - val_loss: 565722.6875
Epoch 2/5
1829/1829 [==============================] - 8s 4ms/step - loss: 402335.1849 - val_loss: 13477191.0000
Epoch 3/5
1829/1829 [==============================] - 8s 4ms/step - loss: 4485.5052 - val_loss: 14826591.0000
Epoch 4/5
1829/1829 [==============================] - 8s 4ms/step - loss: 16302.8976 - val_loss: 14276313.0000
Epoch 5/5
1829/1829 [==============================] - 8s 5ms/step - loss: 6684.3991 - val_loss: 14140148.0000

<tensorflow.python.keras.callbacks.History at 0x196780c1be0>

print("\n\n==================================================")
print("           TIME TAKEN BY GRU               ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(10, 5)
plt.plot(plottime(timetaken_GRU_Model_pos_x.times,timetaken_GRU_Model_pos_y.times,timetaken_GRU_Model_speed.times,timetaken_GRU_Model_energy.times))
plt.title('TIME')
plt.legend(['POS X','POS Y', "SPEED", "ENERGY"], loc='upper left')
plt.xlabel('Epochs')
plt.ylabel('Time (seconds)')
plt.show()

==================================================
           TIME TAKEN BY GRU               
==================================================

Predictions

train_predict_GRU_Model_pos_x = GRU_Model_pos_x.predict(X_training_data_reshaped)
test_predict_GRU_Model_pos_x = GRU_Model_pos_x.predict(X_testing_data_reshaped)

train_predict_GRU_Model_pos_y = GRU_Model_pos_y.predict(X_training_data_reshaped)
test_predict_GRU_Model_pos_y = GRU_Model_pos_y.predict(X_testing_data_reshaped)

train_predict_GRU_Model_speed = GRU_Model_speed.predict(X_training_data_reshaped)
test_predict_GRU_Model_speed = GRU_Model_speed.predict(X_testing_data_reshaped)

train_predict_GRU_Model_energy = GRU_Model_energy.predict(X_training_data_reshaped)
test_predict_GRU_Model_energy = GRU_Model_energy.predict(X_testing_data_reshaped)

print("\n\nPredictions Returned by GRU: ")
print("===========================\n\n")
df_prediction_GRU = pd.DataFrame()
df_prediction_GRU["Pos X Actual"] = y_testing_data_pos_x
df_prediction_GRU["Pos X Predicted"] = test_predict_GRU_Model_pos_x
df_prediction_GRU["Pos Y Actual"] = y_testing_data_pos_y
df_prediction_GRU["Pos Y Predicted"] = test_predict_GRU_Model_pos_y
df_prediction_GRU["Speed Actual"] = y_testing_data_speed
df_prediction_GRU["Speed Predicted"] = test_predict_GRU_Model_speed
df_prediction_GRU["Energy Actual"] = y_testing_data_energy
df_prediction_GRU["Energy Predicted"] = test_predict_GRU_Model_energy
print(df_prediction_GRU)

Predictions Returned by GRU: 
===========================


       Pos X Actual  Pos X Predicted  Pos Y Actual  Pos Y Predicted  \
0           204.428       200.905029       583.988       581.660461   
1           204.428       200.905029       583.988       581.660461   
2           204.428       200.905029       583.988       581.660461   
3           204.428       200.905029       583.988       581.660461   
4           204.428       200.905029       583.988       581.660461   
...             ...              ...           ...              ...   
17994       210.673       205.124252       468.992       474.183105   
17995       210.673       205.124252       468.992       474.183105   
17996       210.673       205.124268       468.992       474.183075   
17997       210.673       205.124268       468.992       474.183075   
17998       210.673       205.124268       468.992       474.183075   

       Speed Actual  Speed Predicted  Energy Actual  Energy Predicted  
0               0.0         0.151448            0.0          3.910618  
1               0.0         0.151448            0.0          3.910618  
2               0.0         0.151448            0.0          3.910618  
3               0.0         0.151448            0.0          3.910618  
4               0.0         0.151448            0.0          3.910618  
...             ...              ...            ...               ...  
17994           0.0         0.101021            0.0         -7.463221  
17995           0.0         0.101021            0.0         -7.463221  
17996           0.0         0.101021            0.0         -7.463707  
17997           0.0         0.101021            0.0         -7.463707  
17998           0.0         0.101021            0.0         -7.463707  

[17999 rows x 8 columns]

RMSE

print("\n\nRMSE on Training Data by GRU: ")
print("=============================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x,train_predict_GRU_Model_pos_x)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y,train_predict_GRU_Model_pos_y)))
print(math.sqrt(mean_squared_error(y_training_data_speed,train_predict_GRU_Model_speed)))
print(math.sqrt(mean_squared_error(y_training_data_energy,train_predict_GRU_Model_energy)))

print("\n\nRMSE on Testing Data by GRU: ")
print("============================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_GRU_Model_pos_x)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_GRU_Model_pos_y)))
print(math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_GRU_Model_speed)))
print(math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_GRU_Model_energy)))

RMSE on Training Data by GRU: 
=============================


13.462225054992512
12.530817549751713
0.46140659059546146
102.07048211255805


RMSE on Testing Data by GRU: 
============================


20.767906096783808
23.35258700752008
0.6382154593351096
3760.3388405168557

Graph

plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x)
plt.plot(test_predict_GRU_Model_pos_x)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y)
plt.plot(test_predict_GRU_Model_pos_y)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed)
plt.plot(test_predict_GRU_Model_speed)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy)
plt.plot(test_predict_GRU_Model_energy)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

===============================

RNN

===============================

RNN_Model_pos_x = Sequential()
RNN_Model_pos_x.add(RNN(50,input_shape=(4,1)))
RNN_Model_pos_x.add(Dense(1))
RNN_Model_pos_x.compile(loss='mean_squared_error',optimizer='adam')

RNN_Model_pos_y = Sequential()
RNN_Model_pos_y.add(RNN(50,input_shape=(4,1)))
RNN_Model_pos_y.add(Dense(1))
RNN_Model_pos_y.compile(loss='mean_squared_error',optimizer='adam')

RNN_Model_speed = Sequential()
RNN_Model_speed.add(RNN(50,input_shape=(4,1)))
RNN_Model_speed.add(Dense(1))
RNN_Model_speed.compile(loss='mean_squared_error',optimizer='adam')

RNN_Model_energy = Sequential()
RNN_Model_energy.add(RNN(50,input_shape=(4,1)))
RNN_Model_energy.add(Dense(1))
RNN_Model_energy.compile(loss='mean_squared_error',optimizer='adam')

timetaken_RNN_Model_pos_x = timecallback6()
timetaken_RNN_Model_pos_y = timecallback6()
timetaken_RNN_Model_speed = timecallback6()
timetaken_RNN_Model_energy = timecallback6()

RNN_Model_pos_x.fit(X_training_data_reshaped,y_training_data_pos_x,validation_data=(X_testing_data_reshaped,y_testing_data_pos_x),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_RNN_Model_pos_x])
RNN_Model_pos_y.fit(X_training_data_reshaped,y_training_data_pos_y,validation_data=(X_testing_data_reshaped,y_testing_data_pos_y),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_RNN_Model_pos_y])
RNN_Model_speed.fit(X_training_data_reshaped,y_training_data_speed,validation_data=(X_testing_data_reshaped,y_testing_data_speed),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_RNN_Model_speed])
RNN_Model_energy.fit(X_training_data_reshaped,y_training_data_energy,validation_data=(X_testing_data_reshaped,y_testing_data_energy),epochs=5,batch_size=64,verbose=1,callbacks = [timetaken_RNN_Model_energy])

Epoch 1/5
1829/1829 [==============================] - 5s 2ms/step - loss: 82091.0525 - val_loss: 52353.6172
Epoch 2/5
1829/1829 [==============================] - 4s 2ms/step - loss: 46589.9719 - val_loss: 30993.6055
Epoch 3/5
1829/1829 [==============================] - 4s 2ms/step - loss: 28075.9146 - val_loss: 21760.8750
Epoch 4/5
1829/1829 [==============================] - 4s 2ms/step - loss: 20309.5089 - val_loss: 19711.5820
Epoch 5/5
1829/1829 [==============================] - 4s 2ms/step - loss: 18878.2562 - val_loss: 19679.3555

Epoch 1/5
1829/1829 [==============================] - 5s 2ms/step - loss: 76874.5766 - val_loss: 49447.6797
Epoch 2/5
1829/1829 [==============================] - 3s 2ms/step - loss: 45325.8946 - val_loss: 32357.0801
Epoch 3/5
1829/1829 [==============================] - 3s 2ms/step - loss: 29675.6622 - val_loss: 17215.0059
Epoch 4/5
1829/1829 [==============================] - 4s 2ms/step - loss: 14724.7751 - val_loss: 8936.5225
Epoch 5/5
1829/1829 [==============================] - 3s 2ms/step - loss: 7246.8284 - val_loss: 4405.6182

Epoch 1/5
1829/1829 [==============================] - 4s 2ms/step - loss: 1.4379 - val_loss: 0.3919
Epoch 2/5
1829/1829 [==============================] - 3s 2ms/step - loss: 0.2251 - val_loss: 0.3820
Epoch 3/5
1829/1829 [==============================] - 4s 2ms/step - loss: 0.2197 - val_loss: 0.4218
Epoch 4/5
1829/1829 [==============================] - 4s 2ms/step - loss: 0.2367 - val_loss: 0.3816
Epoch 5/5
1829/1829 [==============================] - 4s 2ms/step - loss: 0.2169 - val_loss: 0.3835

Epoch 1/5
1829/1829 [==============================] - 5s 2ms/step - loss: 1487424.9823 - val_loss: 490565.5312
Epoch 2/5
1829/1829 [==============================] - 4s 2ms/step - loss: 1303545.3883 - val_loss: 428456.6250
Epoch 3/5
1829/1829 [==============================] - 3s 2ms/step - loss: 1160715.3786 - val_loss: 382815.1562
Epoch 4/5
1829/1829 [==============================] - 3s 2ms/step - loss: 1032413.1282 - val_loss: 352662.9688
Epoch 5/5
1829/1829 [==============================] - 3s 2ms/step - loss: 925062.3181 - val_loss: 337570.0625

<tensorflow.python.keras.callbacks.History at 0x196bba11a60>

print("\n\n==================================================")
print("           TIME TAKEN BY RNN               ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(10, 5)
plt.plot(plottime(timetaken_RNN_Model_pos_x.times,timetaken_RNN_Model_pos_y.times,timetaken_RNN_Model_speed.times,timetaken_RNN_Model_energy.times))
plt.title('TIME')
plt.legend(['POS X','POS Y', "SPEED", "ENERGY"], loc='upper left')
plt.xlabel('Epochs')
plt.ylabel('Time (seconds)')
plt.show()

==================================================
           TIME TAKEN BY RNN               
==================================================

Predictions

train_predict_RNN_Model_pos_x = RNN_Model_pos_x.predict(X_training_data_reshaped)
test_predict_RNN_Model_pos_x = RNN_Model_pos_x.predict(X_testing_data_reshaped)

train_predict_RNN_Model_pos_y = RNN_Model_pos_y.predict(X_training_data_reshaped)
test_predict_RNN_Model_pos_y = RNN_Model_pos_y.predict(X_testing_data_reshaped)

train_predict_RNN_Model_speed = RNN_Model_speed.predict(X_training_data_reshaped)
test_predict_RNN_Model_speed = RNN_Model_speed.predict(X_testing_data_reshaped)

train_predict_RNN_Model_energy = RNN_Model_energy.predict(X_training_data_reshaped)
test_predict_RNN_Model_energy = RNN_Model_energy.predict(X_testing_data_reshaped)

print("\n\nPredictions Returned by RNN: ")
print("===========================\n\n")
df_prediction_RNN = pd.DataFrame()
df_prediction_RNN["Pos X Actual"] = y_testing_data_pos_x
df_prediction_RNN["Pos X Predicted"] = test_predict_RNN_Model_pos_x
df_prediction_RNN["Pos Y Actual"] = y_testing_data_pos_y
df_prediction_RNN["Pos Y Predicted"] = test_predict_RNN_Model_pos_y
df_prediction_RNN["Speed Actual"] = y_testing_data_speed
df_prediction_RNN["Speed Predicted"] = test_predict_RNN_Model_speed
df_prediction_RNN["Energy Actual"] = y_testing_data_energy
df_prediction_RNN["Energy Predicted"] = test_predict_RNN_Model_energy
print(df_prediction_RNN)

Predictions Returned by RNN: 
===========================


       Pos X Actual  Pos X Predicted  Pos Y Actual  Pos Y Predicted  \
0           204.428        282.02478       583.988       375.582581   
1           204.428        282.02478       583.988       375.582581   
2           204.428        282.02478       583.988       375.582581   
3           204.428        282.02478       583.988       375.582581   
4           204.428        282.02478       583.988       375.582581   
...             ...              ...           ...              ...   
17994       210.673        282.02478       468.992       375.575012   
17995       210.673        282.02478       468.992       375.575012   
17996       210.673        282.02475       468.992       375.575012   
17997       210.673        282.02475       468.992       375.575012   
17998       210.673        282.02475       468.992       375.575012   

       Speed Actual  Speed Predicted  Energy Actual  Energy Predicted  
0               0.0         0.154989            0.0        451.353912  
1               0.0         0.154989            0.0        451.353912  
2               0.0         0.154989            0.0        451.353912  
3               0.0         0.154989            0.0        451.353912  
4               0.0         0.154989            0.0        451.353912  
...             ...              ...            ...               ...  
17994           0.0         0.132077            0.0        451.353912  
17995           0.0         0.132077            0.0        451.353912  
17996           0.0         0.132077            0.0        451.353912  
17997           0.0         0.132077            0.0        451.353912  
17998           0.0         0.132077            0.0        451.353912  

[17999 rows x 8 columns]

RMSE

print("\n\nRMSE on Training Data by RNN: ")
print("=============================\n\n")
print(math.sqrt(mean_squared_error(y_training_data_pos_x,train_predict_RNN_Model_pos_x)))
print(math.sqrt(mean_squared_error(y_training_data_pos_y,train_predict_RNN_Model_pos_y)))
print(math.sqrt(mean_squared_error(y_training_data_speed,train_predict_RNN_Model_speed)))
print(math.sqrt(mean_squared_error(y_training_data_energy,train_predict_RNN_Model_energy)))

print("\n\nRMSE on Testing Data by RNN: ")
print("============================\n\n")
print(math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_RNN_Model_pos_x)))
print(math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_RNN_Model_pos_y)))
print(math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_RNN_Model_speed)))
print(math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_RNN_Model_energy)))

RMSE on Training Data by RNN: 
=============================


137.11162163281298
63.39358581503732
0.46551843532375475
922.0456342396242


RMSE on Testing Data by RNN: 
============================


140.2831228889263
66.37482678974489
0.6192413369862964
581.0078232728362

Graph

plt.figure()
fig = plt.gcf()
fig.set_size_inches(12, 8)
plt.subplot(221)
plt.plot(y_testing_data_pos_x)
plt.plot(test_predict_RNN_Model_pos_x)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.grid(True)

plt.subplot(222)
plt.plot(y_testing_data_pos_y)
plt.plot(test_predict_RNN_Model_pos_y)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.grid(True)

plt.subplot(223)
plt.plot(y_testing_data_speed)
plt.plot(test_predict_RNN_Model_speed)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.grid(True)

plt.subplot(224)
plt.plot(y_testing_data_energy)
plt.plot(test_predict_RNN_Model_energy)
plt.legend(['Actual','Predicted'], loc='upper left')
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.grid(True)

plt.subplots_adjust(top=0.92, bottom=0.08, left=0.10, right=0.95, hspace=0.5,wspace=0.35)
plt.show()

!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

Difference Between 6 Algorithms

!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

Dataset Used For comparison

print("\n\nMain Datasets of Node 7 that is Used:")
print("=====================================\n\n")
print("Training Data:\n\n")
print(all_data_training)
print("\n\nTesting Data:\n\n")
print(all_data_node_7_testing)

print("\n\nMain Datasets of Node 15 that is Used:")
print("=====================================\n\n")
print("Training Data:\n\n")
print(all_data_training)
print("\n\nTesting Data:\n\n")
print(all_data_node_15_testing)

print("\n\nMain Datasets of Node 24 that is Used:")
print("=====================================\n\n")
print("Training Data:\n\n")
print(all_data_training)
print("\n\nTesting Data:\n\n")
print(all_data_node_24_testing)

print("\n\nMain Datasets of Node 33 that is Used:")
print("=====================================\n\n")
print("Training Data:\n\n")
print(all_data_training)
print("\n\nTesting Data:\n\n")
print(all_data_node_33_testing)

print("\n\nMain Datasets of Node 48 that is Used:")
print("=====================================\n\n")
print("Training Data:\n\n")
print(all_data_training)
print("\n\nTesting Data:\n\n")
print(all_data_node_48_testing)

Main Datasets of Node 7 that is Used:
=====================================


Training Data:


          pos_x    pos_y     speed      energy
0       307.922  503.508  0.000000  121.188655
1       307.871  503.345  1.974358  120.165500
2       306.494  504.296  1.974358  119.142345
3       305.116  505.246  1.974358  118.119190
4       303.738  506.197  1.974358  117.096035
...         ...      ...       ...         ...
116995  223.377  451.449  1.591080  294.398640
116996  223.885  450.748  1.591080  290.438050
116997  224.393  450.046  1.591080  286.477460
116998  224.901  449.344  1.591080  282.516870
116999  225.409  448.643  1.591080  278.556280

[117000 rows x 4 columns]


Testing Data:


       pos_x    pos_y     speed     energy
0    158.247  254.898  7.842828  210.08317
1    159.187  256.305  7.842828  202.52120
2    160.127  257.712  7.842828  194.95923
3    161.067  259.119  7.842828  187.39726
4    162.007  260.526  7.842828  179.83529
..       ...      ...       ...        ...
295  255.364  120.883  0.000000    0.00000
296  255.364  120.883  0.000000    0.00000
297  255.364  120.883  0.000000    0.00000
298  255.364  120.883  0.000000    0.00000
299  255.364  120.883  0.000000    0.00000

[300 rows x 4 columns]


Main Datasets of Node 15 that is Used:
=====================================


Training Data:


          pos_x    pos_y     speed      energy
0       307.922  503.508  0.000000  121.188655
1       307.871  503.345  1.974358  120.165500
2       306.494  504.296  1.974358  119.142345
3       305.116  505.246  1.974358  118.119190
4       303.738  506.197  1.974358  117.096035
...         ...      ...       ...         ...
116995  223.377  451.449  1.591080  294.398640
116996  223.885  450.748  1.591080  290.438050
116997  224.393  450.046  1.591080  286.477460
116998  224.901  449.344  1.591080  282.516870
116999  225.409  448.643  1.591080  278.556280

[117000 rows x 4 columns]


Testing Data:


       pos_x    pos_y  speed  energy
0    171.695  241.496    0.0     0.0
1    171.695  241.496    0.0     0.0
2    171.695  241.496    0.0     0.0
3    171.695  241.496    0.0     0.0
4    171.695  241.496    0.0     0.0
..       ...      ...    ...     ...
295  257.261  229.576    0.0     0.0
296  257.261  229.576    0.0     0.0
297  257.261  229.576    0.0     0.0
298  257.261  229.576    0.0     0.0
299  257.261  229.576    0.0     0.0

[300 rows x 4 columns]


Main Datasets of Node 24 that is Used:
=====================================


Training Data:


          pos_x    pos_y     speed      energy
0       307.922  503.508  0.000000  121.188655
1       307.871  503.345  1.974358  120.165500
2       306.494  504.296  1.974358  119.142345
3       305.116  505.246  1.974358  118.119190
4       303.738  506.197  1.974358  117.096035
...         ...      ...       ...         ...
116995  223.377  451.449  1.591080  294.398640
116996  223.885  450.748  1.591080  290.438050
116997  224.393  450.046  1.591080  286.477460
116998  224.901  449.344  1.591080  282.516870
116999  225.409  448.643  1.591080  278.556280

[117000 rows x 4 columns]


Testing Data:


       pos_x    pos_y     speed       energy
0    384.720  73.9024  2.405508   775.181610
1    385.183  74.5785  2.405508   773.047275
2    385.646  75.2545  2.405508   770.912940
3    386.109  75.9306  2.405508   768.778605
4    386.572  76.6066  2.405508   766.644270
..       ...      ...       ...          ...
295  382.406  70.5222  7.435760  1467.316100
296  382.869  71.1982  7.435760  1463.320168
297  383.332  71.8743  7.435760  1459.324236
298  383.794  72.5503  7.435760  1455.328304
299  384.257  73.2264  7.435760  1451.332372

[300 rows x 4 columns]


Main Datasets of Node 33 that is Used:
=====================================


Training Data:


          pos_x    pos_y     speed      energy
0       307.922  503.508  0.000000  121.188655
1       307.871  503.345  1.974358  120.165500
2       306.494  504.296  1.974358  119.142345
3       305.116  505.246  1.974358  118.119190
4       303.738  506.197  1.974358  117.096035
...         ...      ...       ...         ...
116995  223.377  451.449  1.591080  294.398640
116996  223.885  450.748  1.591080  290.438050
116997  224.393  450.046  1.591080  286.477460
116998  224.901  449.344  1.591080  282.516870
116999  225.409  448.643  1.591080  278.556280

[117000 rows x 4 columns]


Testing Data:


       pos_x    pos_y     speed      energy
0    248.615  316.373  1.463984  228.579050
1    249.988  316.303  1.463984  226.445967
2    251.361  316.234  1.463984  224.312884
3    252.734  316.164  1.463984  222.179801
4    254.107  316.095  1.463984  220.046718
..       ...      ...       ...         ...
295  377.419  194.029  6.626459  347.367962
296  378.576  195.316  6.626459  347.029591
297  379.733  196.603  6.626459  346.691220
298  380.890  197.890  6.626459  346.352849
299  382.047  199.177  6.626459  346.014478

[300 rows x 4 columns]


Main Datasets of Node 48 that is Used:
=====================================


Training Data:


          pos_x    pos_y     speed      energy
0       307.922  503.508  0.000000  121.188655
1       307.871  503.345  1.974358  120.165500
2       306.494  504.296  1.974358  119.142345
3       305.116  505.246  1.974358  118.119190
4       303.738  506.197  1.974358  117.096035
...         ...      ...       ...         ...
116995  223.377  451.449  1.591080  294.398640
116996  223.885  450.748  1.591080  290.438050
116997  224.393  450.046  1.591080  286.477460
116998  224.901  449.344  1.591080  282.516870
116999  225.409  448.643  1.591080  278.556280

[117000 rows x 4 columns]


Testing Data:


       pos_x    pos_y     speed      energy
0    393.463  154.932  5.970805  903.785894
1    393.724  154.969  5.970805  898.273815
2    393.985  155.007  5.970805  892.761735
3    394.246  155.044  5.970805  887.249655
4    394.506  155.082  5.970805  881.737575
..       ...      ...       ...         ...
295  392.159  154.745  7.440762  493.946780
296  392.420  154.782  7.440762  488.584160
297  392.681  154.820  7.440762  483.221540
298  392.941  154.857  7.440762  477.858920
299  393.202  154.894  7.440762  472.496300

[300 rows x 4 columns]

Node 7

=======

test_predict_Stacked_LSTM_Model_pos_x_2_node_7 = Stacked_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_7)
test_predict_Stacked_LSTM_Model_pos_y_2_node_7 = Stacked_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_7)
test_predict_Stacked_LSTM_Model_speed_2_node_7 = Stacked_LSTM_Model_speed.predict(X_testing_data_reshaped_node_7)
test_predict_Stacked_LSTM_Model_energy_2_node_7 = Stacked_LSTM_Model_energy.predict(X_testing_data_reshaped_node_7)

test_predict_CNN_LSTM_Model_pos_x_2_node_7 = CNN_LSTM_Model_pos_x.predict(X_testing_data_reshaped_cnn_node_7)
test_predict_CNN_LSTM_Model_pos_y_2_node_7 = CNN_LSTM_Model_pos_y.predict(X_testing_data_reshaped_cnn_node_7)
test_predict_CNN_LSTM_Model_speed_2_node_7 = CNN_LSTM_Model_speed.predict(X_testing_data_reshaped_cnn_node_7)
test_predict_CNN_LSTM_Model_energy_2_node_7 = CNN_LSTM_Model_energy.predict(X_testing_data_reshaped_cnn_node_7)

test_predict_LSTM_Model_pos_x_2_node_7 = LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_7)
test_predict_LSTM_Model_pos_y_2_node_7 = LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_7)
test_predict_LSTM_Model_speed_2_node_7 = LSTM_Model_speed.predict(X_testing_data_reshaped_node_7)
test_predict_LSTM_Model_energy_2_node_7 = LSTM_Model_energy.predict(X_testing_data_reshaped_node_7)

test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_7 = BiDirectonal_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_7)
test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_7 = BiDirectonal_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_7)
test_predict_BiDirectonal_LSTM_Model_speed_2_node_7 = BiDirectonal_LSTM_Model_speed.predict(X_testing_data_reshaped_node_7)
test_predict_BiDirectonal_LSTM_Model_energy_2_node_7 = BiDirectonal_LSTM_Model_energy.predict(X_testing_data_reshaped_node_7)

test_predict_GRU_Model_pos_x_2_node_7 = GRU_Model_pos_x.predict(X_testing_data_reshaped_node_7)
test_predict_GRU_Model_pos_y_2_node_7 = GRU_Model_pos_y.predict(X_testing_data_reshaped_node_7)
test_predict_GRU_Model_speed_2_node_7 = GRU_Model_speed.predict(X_testing_data_reshaped_node_7)
test_predict_GRU_Model_energy_2_node_7 = GRU_Model_energy.predict(X_testing_data_reshaped_node_7)

test_predict_RNN_Model_pos_x_2_node_7 = RNN_Model_pos_x.predict(X_testing_data_reshaped_node_7)
test_predict_RNN_Model_pos_y_2_node_7 = RNN_Model_pos_y.predict(X_testing_data_reshaped_node_7)
test_predict_RNN_Model_speed_2_node_7 = RNN_Model_speed.predict(X_testing_data_reshaped_node_7)
test_predict_RNN_Model_energy_2_node_7 = RNN_Model_energy.predict(X_testing_data_reshaped_node_7)

print("\n\n==================================================")
print("       PREDICITED POS X BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_pos_x_node_7)
plt.plot(test_predict_Stacked_LSTM_Model_pos_x_2_node_7)
plt.plot(test_predict_CNN_LSTM_Model_pos_x_2_node_7)
plt.plot(test_predict_LSTM_Model_pos_x_2_node_7)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_7)
plt.plot(test_predict_GRU_Model_pos_x_2_node_7)
plt.plot(test_predict_RNN_Model_pos_x_2_node_7)
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED POS Y BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_pos_y_node_7)
plt.plot(test_predict_Stacked_LSTM_Model_pos_y_2_node_7)
plt.plot(test_predict_CNN_LSTM_Model_pos_y_2_node_7)
plt.plot(test_predict_LSTM_Model_pos_y_2_node_7)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_7)
plt.plot(test_predict_GRU_Model_pos_y_2_node_7)
plt.plot(test_predict_RNN_Model_pos_y_2_node_7)
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED SPEED BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_speed_node_7)
plt.plot(test_predict_Stacked_LSTM_Model_speed_2_node_7)
plt.plot(test_predict_CNN_LSTM_Model_speed_2_node_7)
plt.plot(test_predict_LSTM_Model_speed_2_node_7)
plt.plot(test_predict_BiDirectonal_LSTM_Model_speed_2_node_7)
plt.plot(test_predict_GRU_Model_speed_2_node_7)
plt.plot(test_predict_RNN_Model_speed_2_node_7)
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED ENERGY BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_energy_node_7)
plt.plot(test_predict_Stacked_LSTM_Model_energy_2_node_7)
plt.plot(test_predict_CNN_LSTM_Model_energy_2_node_7)
plt.plot(test_predict_LSTM_Model_energy_2_node_7)
plt.plot(test_predict_BiDirectonal_LSTM_Model_energy_2_node_7)
plt.plot(test_predict_GRU_Model_energy_2_node_7)
plt.plot(test_predict_RNN_Model_energy_2_node_7)
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()

==================================================
       PREDICITED POS X BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED POS Y BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED SPEED BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED ENERGY BY ALL ALGORITHMS     
==================================================

print("\n\nROOT MEAN SQUARE OF ALL ALGORITHMS:")
print("====================================\n")

pretty_table_RMSE = PrettyTable()
pretty_table_RMSE.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])

pretty_table_RMSE.add_column("Pos X RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_Stacked_LSTM_Model_pos_x_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_CNN_LSTM_Model_pos_x_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_LSTM_Model_pos_x_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_GRU_Model_pos_x_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_RNN_Model_pos_x_2_node_7))),2)])

pretty_table_RMSE.add_column("Pos Y RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_Stacked_LSTM_Model_pos_y_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_CNN_LSTM_Model_pos_y_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_LSTM_Model_pos_y_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_GRU_Model_pos_y_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_RNN_Model_pos_y_2_node_7))),2)])

pretty_table_RMSE.add_column("Speed RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_Stacked_LSTM_Model_speed_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_CNN_LSTM_Model_speed_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_LSTM_Model_speed_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_BiDirectonal_LSTM_Model_speed_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_GRU_Model_speed_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_RNN_Model_speed_2_node_7))),2)])

pretty_table_RMSE.add_column("Energy RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_Stacked_LSTM_Model_energy_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_CNN_LSTM_Model_energy_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_LSTM_Model_energy_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_BiDirectonal_LSTM_Model_energy_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_GRU_Model_energy_2_node_7))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_RNN_Model_energy_2_node_7))),2)])

print(pretty_table_RMSE)

ROOT MEAN SQUARE OF ALL ALGORITHMS:
====================================

+-------------------+------------+------------+------------+-------------+
|     Algorithm     | Pos X RMSE | Pos Y RMSE | Speed RMSE | Energy RMSE |
+-------------------+------------+------------+------------+-------------+
|    Stacked_LSTM   |   79.72    |   121.01   |   174.16   |    300.37   |
|      CNN_LSTM     |   137.77   |   203.01   |   174.21   |    691.21   |
|        LSTM       |   77.14    |   152.01   |   174.23   |    302.49   |
| BiDirectonal_LSTM |   189.16   |   217.01   |   173.8    |   1981.37   |
|        GRU        |   176.86   |   218.85   |   174.15   |   2027.62   |
|        RNN        |   140.88   |   197.14   |   174.11   |    299.8    |
+-------------------+------------+------------+------------+-------------+

Node 15

=======

test_predict_Stacked_LSTM_Model_pos_x_2_node_15 = Stacked_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_15)
test_predict_Stacked_LSTM_Model_pos_y_2_node_15 = Stacked_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_15)
test_predict_Stacked_LSTM_Model_speed_2_node_15 = Stacked_LSTM_Model_speed.predict(X_testing_data_reshaped_node_15)
test_predict_Stacked_LSTM_Model_energy_2_node_15 = Stacked_LSTM_Model_energy.predict(X_testing_data_reshaped_node_15)

test_predict_CNN_LSTM_Model_pos_x_2_node_15 = CNN_LSTM_Model_pos_x.predict(X_testing_data_reshaped_cnn_node_15)
test_predict_CNN_LSTM_Model_pos_y_2_node_15 = CNN_LSTM_Model_pos_y.predict(X_testing_data_reshaped_cnn_node_15)
test_predict_CNN_LSTM_Model_speed_2_node_15 = CNN_LSTM_Model_speed.predict(X_testing_data_reshaped_cnn_node_15)
test_predict_CNN_LSTM_Model_energy_2_node_15 = CNN_LSTM_Model_energy.predict(X_testing_data_reshaped_cnn_node_15)

test_predict_LSTM_Model_pos_x_2_node_15 = LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_15)
test_predict_LSTM_Model_pos_y_2_node_15 = LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_15)
test_predict_LSTM_Model_speed_2_node_15 = LSTM_Model_speed.predict(X_testing_data_reshaped_node_15)
test_predict_LSTM_Model_energy_2_node_15 = LSTM_Model_energy.predict(X_testing_data_reshaped_node_15)

test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_15 = BiDirectonal_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_15)
test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_15 = BiDirectonal_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_15)
test_predict_BiDirectonal_LSTM_Model_speed_2_node_15 = BiDirectonal_LSTM_Model_speed.predict(X_testing_data_reshaped_node_15)
test_predict_BiDirectonal_LSTM_Model_energy_2_node_15 = BiDirectonal_LSTM_Model_energy.predict(X_testing_data_reshaped_node_15)

test_predict_GRU_Model_pos_x_2_node_15 = GRU_Model_pos_x.predict(X_testing_data_reshaped_node_15)
test_predict_GRU_Model_pos_y_2_node_15 = GRU_Model_pos_y.predict(X_testing_data_reshaped_node_15)
test_predict_GRU_Model_speed_2_node_15 = GRU_Model_speed.predict(X_testing_data_reshaped_node_15)
test_predict_GRU_Model_energy_2_node_15 = GRU_Model_energy.predict(X_testing_data_reshaped_node_15)

test_predict_RNN_Model_pos_x_2_node_15 = RNN_Model_pos_x.predict(X_testing_data_reshaped_node_15)
test_predict_RNN_Model_pos_y_2_node_15 = RNN_Model_pos_y.predict(X_testing_data_reshaped_node_15)
test_predict_RNN_Model_speed_2_node_15 = RNN_Model_speed.predict(X_testing_data_reshaped_node_15)
test_predict_RNN_Model_energy_2_node_15 = RNN_Model_energy.predict(X_testing_data_reshaped_node_15)

print("\n\n==================================================")
print("       PREDICITED POS X BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_pos_x_node_15)
plt.plot(test_predict_Stacked_LSTM_Model_pos_x_2_node_15)
plt.plot(test_predict_CNN_LSTM_Model_pos_x_2_node_15)
plt.plot(test_predict_LSTM_Model_pos_x_2_node_15)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_15)
plt.plot(test_predict_GRU_Model_pos_x_2_node_15)
plt.plot(test_predict_RNN_Model_pos_x_2_node_15)
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED POS Y BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_pos_y_node_15)
plt.plot(test_predict_Stacked_LSTM_Model_pos_y_2_node_15)
plt.plot(test_predict_CNN_LSTM_Model_pos_y_2_node_15)
plt.plot(test_predict_LSTM_Model_pos_y_2_node_15)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_15)
plt.plot(test_predict_GRU_Model_pos_y_2_node_15)
plt.plot(test_predict_RNN_Model_pos_y_2_node_15)
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED SPEED BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_speed_node_15)
plt.plot(test_predict_Stacked_LSTM_Model_speed_2_node_15)
plt.plot(test_predict_CNN_LSTM_Model_speed_2_node_15)
plt.plot(test_predict_LSTM_Model_speed_2_node_15)
plt.plot(test_predict_BiDirectonal_LSTM_Model_speed_2_node_15)
plt.plot(test_predict_GRU_Model_speed_2_node_15)
plt.plot(test_predict_RNN_Model_speed_2_node_15)
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED ENERGY BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_energy_node_15)
plt.plot(test_predict_Stacked_LSTM_Model_energy_2_node_15)
plt.plot(test_predict_CNN_LSTM_Model_energy_2_node_15)
plt.plot(test_predict_LSTM_Model_energy_2_node_15)
plt.plot(test_predict_BiDirectonal_LSTM_Model_energy_2_node_15)
plt.plot(test_predict_GRU_Model_energy_2_node_15)
plt.plot(test_predict_RNN_Model_energy_2_node_15)
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()

==================================================
       PREDICITED POS X BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED POS Y BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED SPEED BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED ENERGY BY ALL ALGORITHMS     
==================================================

print("\n\nROOT MEAN SQUARE OF ALL ALGORITHMS:")
print("====================================\n")

pretty_table_RMSE = PrettyTable()
pretty_table_RMSE.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])

pretty_table_RMSE.add_column("Pos X RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_Stacked_LSTM_Model_pos_x_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_CNN_LSTM_Model_pos_x_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_LSTM_Model_pos_x_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_GRU_Model_pos_x_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_RNN_Model_pos_x_2_node_15))),2)])

pretty_table_RMSE.add_column("Pos Y RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_Stacked_LSTM_Model_pos_y_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_CNN_LSTM_Model_pos_y_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_LSTM_Model_pos_y_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_GRU_Model_pos_y_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_RNN_Model_pos_y_2_node_15))),2)])

pretty_table_RMSE.add_column("Speed RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_Stacked_LSTM_Model_speed_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_CNN_LSTM_Model_speed_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_LSTM_Model_speed_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_BiDirectonal_LSTM_Model_speed_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_GRU_Model_speed_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_RNN_Model_speed_2_node_15))),2)])

pretty_table_RMSE.add_column("Energy RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_Stacked_LSTM_Model_energy_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_CNN_LSTM_Model_energy_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_LSTM_Model_energy_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_BiDirectonal_LSTM_Model_energy_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_GRU_Model_energy_2_node_15))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_RNN_Model_energy_2_node_15))),2)])

print(pretty_table_RMSE)

ROOT MEAN SQUARE OF ALL ALGORITHMS:
====================================

+-------------------+------------+------------+------------+-------------+
|     Algorithm     | Pos X RMSE | Pos Y RMSE | Speed RMSE | Energy RMSE |
+-------------------+------------+------------+------------+-------------+
|    Stacked_LSTM   |   111.92   |   79.17    |   201.39   |    259.79   |
|      CNN_LSTM     |   125.47   |   179.42   |   201.18   |    782.59   |
|        LSTM       |   111.05   |   99.66    |   201.41   |    261.94   |
| BiDirectonal_LSTM |   206.23   |   175.99   |   197.89   |   4052.58   |
|        GRU        |   200.65   |   147.07   |   201.33   |   4343.67   |
|        RNN        |    98.6    |   122.92   |   201.42   |    259.21   |
+-------------------+------------+------------+------------+-------------+

Node 24

=======

test_predict_Stacked_LSTM_Model_pos_x_2_node_24 = Stacked_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_24)
test_predict_Stacked_LSTM_Model_pos_y_2_node_24 = Stacked_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_24)
test_predict_Stacked_LSTM_Model_speed_2_node_24 = Stacked_LSTM_Model_speed.predict(X_testing_data_reshaped_node_24)
test_predict_Stacked_LSTM_Model_energy_2_node_24 = Stacked_LSTM_Model_energy.predict(X_testing_data_reshaped_node_24)

test_predict_CNN_LSTM_Model_pos_x_2_node_24 = CNN_LSTM_Model_pos_x.predict(X_testing_data_reshaped_cnn_node_24)
test_predict_CNN_LSTM_Model_pos_y_2_node_24 = CNN_LSTM_Model_pos_y.predict(X_testing_data_reshaped_cnn_node_24)
test_predict_CNN_LSTM_Model_speed_2_node_24 = CNN_LSTM_Model_speed.predict(X_testing_data_reshaped_cnn_node_24)
test_predict_CNN_LSTM_Model_energy_2_node_24 = CNN_LSTM_Model_energy.predict(X_testing_data_reshaped_cnn_node_24)

test_predict_LSTM_Model_pos_x_2_node_24 = LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_24)
test_predict_LSTM_Model_pos_y_2_node_24 = LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_24)
test_predict_LSTM_Model_speed_2_node_24 = LSTM_Model_speed.predict(X_testing_data_reshaped_node_24)
test_predict_LSTM_Model_energy_2_node_24 = LSTM_Model_energy.predict(X_testing_data_reshaped_node_24)

test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_24 = BiDirectonal_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_24)
test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_24 = BiDirectonal_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_24)
test_predict_BiDirectonal_LSTM_Model_speed_2_node_24 = BiDirectonal_LSTM_Model_speed.predict(X_testing_data_reshaped_node_24)
test_predict_BiDirectonal_LSTM_Model_energy_2_node_24 = BiDirectonal_LSTM_Model_energy.predict(X_testing_data_reshaped_node_24)

test_predict_GRU_Model_pos_x_2_node_24 = GRU_Model_pos_x.predict(X_testing_data_reshaped_node_24)
test_predict_GRU_Model_pos_y_2_node_24 = GRU_Model_pos_y.predict(X_testing_data_reshaped_node_24)
test_predict_GRU_Model_speed_2_node_24 = GRU_Model_speed.predict(X_testing_data_reshaped_node_24)
test_predict_GRU_Model_energy_2_node_24 = GRU_Model_energy.predict(X_testing_data_reshaped_node_24)

test_predict_RNN_Model_pos_x_2_node_24 = RNN_Model_pos_x.predict(X_testing_data_reshaped_node_24)
test_predict_RNN_Model_pos_y_2_node_24 = RNN_Model_pos_y.predict(X_testing_data_reshaped_node_24)
test_predict_RNN_Model_speed_2_node_24 = RNN_Model_speed.predict(X_testing_data_reshaped_node_24)
test_predict_RNN_Model_energy_2_node_24 = RNN_Model_energy.predict(X_testing_data_reshaped_node_24)

print("\n\n==================================================")
print("       PREDICITED POS X BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_pos_x_node_24)
plt.plot(test_predict_Stacked_LSTM_Model_pos_x_2_node_24)
plt.plot(test_predict_CNN_LSTM_Model_pos_x_2_node_24)
plt.plot(test_predict_LSTM_Model_pos_x_2_node_24)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_24)
plt.plot(test_predict_GRU_Model_pos_x_2_node_24)
plt.plot(test_predict_RNN_Model_pos_x_2_node_24)
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED POS Y BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_pos_y_node_24)
plt.plot(test_predict_Stacked_LSTM_Model_pos_y_2_node_24)
plt.plot(test_predict_CNN_LSTM_Model_pos_y_2_node_24)
plt.plot(test_predict_LSTM_Model_pos_y_2_node_24)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_24)
plt.plot(test_predict_GRU_Model_pos_y_2_node_24)
plt.plot(test_predict_RNN_Model_pos_y_2_node_24)
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED SPEED BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_speed_node_24)
plt.plot(test_predict_Stacked_LSTM_Model_speed_2_node_24)
plt.plot(test_predict_CNN_LSTM_Model_speed_2_node_24)
plt.plot(test_predict_LSTM_Model_speed_2_node_24)
plt.plot(test_predict_BiDirectonal_LSTM_Model_speed_2_node_24)
plt.plot(test_predict_GRU_Model_speed_2_node_24)
plt.plot(test_predict_RNN_Model_speed_2_node_24)
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED ENERGY BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_energy_node_24)
plt.plot(test_predict_Stacked_LSTM_Model_energy_2_node_24)
plt.plot(test_predict_CNN_LSTM_Model_energy_2_node_24)
plt.plot(test_predict_LSTM_Model_energy_2_node_24)
plt.plot(test_predict_BiDirectonal_LSTM_Model_energy_2_node_24)
plt.plot(test_predict_GRU_Model_energy_2_node_24)
plt.plot(test_predict_RNN_Model_energy_2_node_24)
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()

==================================================
       PREDICITED POS X BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED POS Y BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED SPEED BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED ENERGY BY ALL ALGORITHMS     
==================================================

print("\n\nROOT MEAN SQUARE OF ALL ALGORITHMS:")
print("====================================\n")

pretty_table_RMSE = PrettyTable()
pretty_table_RMSE.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])

pretty_table_RMSE.add_column("Pos X RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_Stacked_LSTM_Model_pos_x_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_CNN_LSTM_Model_pos_x_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_LSTM_Model_pos_x_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_GRU_Model_pos_x_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_RNN_Model_pos_x_2_node_24))),2)])

pretty_table_RMSE.add_column("Pos Y RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_Stacked_LSTM_Model_pos_y_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_CNN_LSTM_Model_pos_y_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_LSTM_Model_pos_y_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_GRU_Model_pos_y_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_RNN_Model_pos_y_2_node_24))),2)])

pretty_table_RMSE.add_column("Speed RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_Stacked_LSTM_Model_speed_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_CNN_LSTM_Model_speed_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_LSTM_Model_speed_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_BiDirectonal_LSTM_Model_speed_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_GRU_Model_speed_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_RNN_Model_speed_2_node_24))),2)])

pretty_table_RMSE.add_column("Energy RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_Stacked_LSTM_Model_energy_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_CNN_LSTM_Model_energy_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_LSTM_Model_energy_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_BiDirectonal_LSTM_Model_energy_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_GRU_Model_energy_2_node_24))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_RNN_Model_energy_2_node_24))),2)])

print(pretty_table_RMSE)

ROOT MEAN SQUARE OF ALL ALGORITHMS:
====================================

+-------------------+------------+------------+------------+-------------+
|     Algorithm     | Pos X RMSE | Pos Y RMSE | Speed RMSE | Energy RMSE |
+-------------------+------------+------------+------------+-------------+
|    Stacked_LSTM   |   47.41    |   116.83   |   306.42   |    195.78   |
|      CNN_LSTM     |   162.41   |   173.78   |   306.13   |    858.94   |
|        LSTM       |    47.2    |   251.64   |   306.38   |    197.56   |
| BiDirectonal_LSTM |   133.8    |   318.04   |   300.78   |   5463.28   |
|        GRU        |   140.26   |   333.81   |   306.33   |   5577.15   |
|        RNN        |   112.47   |   283.21   |   306.55   |    195.29   |
+-------------------+------------+------------+------------+-------------+

Node 33

=======

test_predict_Stacked_LSTM_Model_pos_x_2_node_33 = Stacked_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_33)
test_predict_Stacked_LSTM_Model_pos_y_2_node_33 = Stacked_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_33)
test_predict_Stacked_LSTM_Model_speed_2_node_33 = Stacked_LSTM_Model_speed.predict(X_testing_data_reshaped_node_33)
test_predict_Stacked_LSTM_Model_energy_2_node_33 = Stacked_LSTM_Model_energy.predict(X_testing_data_reshaped_node_33)

test_predict_CNN_LSTM_Model_pos_x_2_node_33 = CNN_LSTM_Model_pos_x.predict(X_testing_data_reshaped_cnn_node_33)
test_predict_CNN_LSTM_Model_pos_y_2_node_33 = CNN_LSTM_Model_pos_y.predict(X_testing_data_reshaped_cnn_node_33)
test_predict_CNN_LSTM_Model_speed_2_node_33 = CNN_LSTM_Model_speed.predict(X_testing_data_reshaped_cnn_node_33)
test_predict_CNN_LSTM_Model_energy_2_node_33 = CNN_LSTM_Model_energy.predict(X_testing_data_reshaped_cnn_node_33)

test_predict_LSTM_Model_pos_x_2_node_33 = LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_33)
test_predict_LSTM_Model_pos_y_2_node_33 = LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_33)
test_predict_LSTM_Model_speed_2_node_33 = LSTM_Model_speed.predict(X_testing_data_reshaped_node_33)
test_predict_LSTM_Model_energy_2_node_33 = LSTM_Model_energy.predict(X_testing_data_reshaped_node_33)

test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_33 = BiDirectonal_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_33)
test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_33 = BiDirectonal_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_33)
test_predict_BiDirectonal_LSTM_Model_speed_2_node_33 = BiDirectonal_LSTM_Model_speed.predict(X_testing_data_reshaped_node_33)
test_predict_BiDirectonal_LSTM_Model_energy_2_node_33 = BiDirectonal_LSTM_Model_energy.predict(X_testing_data_reshaped_node_33)

test_predict_GRU_Model_pos_x_2_node_33 = GRU_Model_pos_x.predict(X_testing_data_reshaped_node_33)
test_predict_GRU_Model_pos_y_2_node_33 = GRU_Model_pos_y.predict(X_testing_data_reshaped_node_33)
test_predict_GRU_Model_speed_2_node_33 = GRU_Model_speed.predict(X_testing_data_reshaped_node_33)
test_predict_GRU_Model_energy_2_node_33 = GRU_Model_energy.predict(X_testing_data_reshaped_node_33)

test_predict_RNN_Model_pos_x_2_node_33 = RNN_Model_pos_x.predict(X_testing_data_reshaped_node_33)
test_predict_RNN_Model_pos_y_2_node_33 = RNN_Model_pos_y.predict(X_testing_data_reshaped_node_33)
test_predict_RNN_Model_speed_2_node_33 = RNN_Model_speed.predict(X_testing_data_reshaped_node_33)
test_predict_RNN_Model_energy_2_node_33 = RNN_Model_energy.predict(X_testing_data_reshaped_node_33)

print("\n\n==================================================")
print("       PREDICITED POS X BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_pos_x_node_33)
plt.plot(test_predict_Stacked_LSTM_Model_pos_x_2_node_33)
plt.plot(test_predict_CNN_LSTM_Model_pos_x_2_node_33)
plt.plot(test_predict_LSTM_Model_pos_x_2_node_33)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_33)
plt.plot(test_predict_GRU_Model_pos_x_2_node_33)
plt.plot(test_predict_RNN_Model_pos_x_2_node_33)
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED POS Y BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_pos_y_node_33)
plt.plot(test_predict_Stacked_LSTM_Model_pos_y_2_node_33)
plt.plot(test_predict_CNN_LSTM_Model_pos_y_2_node_33)
plt.plot(test_predict_LSTM_Model_pos_y_2_node_33)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_33)
plt.plot(test_predict_GRU_Model_pos_y_2_node_33)
plt.plot(test_predict_RNN_Model_pos_y_2_node_33)
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED SPEED BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_speed_node_33)
plt.plot(test_predict_Stacked_LSTM_Model_speed_2_node_33)
plt.plot(test_predict_CNN_LSTM_Model_speed_2_node_33)
plt.plot(test_predict_LSTM_Model_speed_2_node_33)
plt.plot(test_predict_BiDirectonal_LSTM_Model_speed_2_node_33)
plt.plot(test_predict_GRU_Model_speed_2_node_33)
plt.plot(test_predict_RNN_Model_speed_2_node_33)
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED ENERGY BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_energy_node_33)
plt.plot(test_predict_Stacked_LSTM_Model_energy_2_node_33)
plt.plot(test_predict_CNN_LSTM_Model_energy_2_node_33)
plt.plot(test_predict_LSTM_Model_energy_2_node_33)
plt.plot(test_predict_BiDirectonal_LSTM_Model_energy_2_node_33)
plt.plot(test_predict_GRU_Model_energy_2_node_33)
plt.plot(test_predict_RNN_Model_energy_2_node_33)
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()

==================================================
       PREDICITED POS X BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED POS Y BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED SPEED BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED ENERGY BY ALL ALGORITHMS     
==================================================

print("\n\nROOT MEAN SQUARE OF ALL ALGORITHMS:")
print("====================================\n")

pretty_table_RMSE = PrettyTable()
pretty_table_RMSE.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])

pretty_table_RMSE.add_column("Pos X RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_Stacked_LSTM_Model_pos_x_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_CNN_LSTM_Model_pos_x_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_LSTM_Model_pos_x_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_GRU_Model_pos_x_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_RNN_Model_pos_x_2_node_33))),2)])

pretty_table_RMSE.add_column("Pos Y RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_Stacked_LSTM_Model_pos_y_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_CNN_LSTM_Model_pos_y_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_LSTM_Model_pos_y_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_GRU_Model_pos_y_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_RNN_Model_pos_y_2_node_33))),2)])

pretty_table_RMSE.add_column("Speed RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_Stacked_LSTM_Model_speed_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_CNN_LSTM_Model_speed_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_LSTM_Model_speed_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_BiDirectonal_LSTM_Model_speed_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_GRU_Model_speed_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_RNN_Model_speed_2_node_33))),2)])

pretty_table_RMSE.add_column("Energy RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_Stacked_LSTM_Model_energy_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_CNN_LSTM_Model_energy_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_LSTM_Model_energy_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_BiDirectonal_LSTM_Model_energy_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_GRU_Model_energy_2_node_33))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_RNN_Model_energy_2_node_33))),2)])

print(pretty_table_RMSE)

ROOT MEAN SQUARE OF ALL ALGORITHMS:
====================================

+-------------------+------------+------------+------------+-------------+
|     Algorithm     | Pos X RMSE | Pos Y RMSE | Speed RMSE | Energy RMSE |
+-------------------+------------+------------+------------+-------------+
|    Stacked_LSTM   |   52.69    |   80.69    |   245.85   |    228.73   |
|      CNN_LSTM     |   211.55   |   216.29   |   244.57   |    883.14   |
|        LSTM       |   48.56    |   150.45   |   245.73   |    230.78   |
| BiDirectonal_LSTM |    85.7    |   368.61   |   240.27   |    6513.8   |
|        GRU        |   82.98    |   336.41   |   245.6    |   6190.81   |
|        RNN        |   89.92    |   186.94   |   245.81   |    228.18   |
+-------------------+------------+------------+------------+-------------+

Node 48

=======

test_predict_Stacked_LSTM_Model_pos_x_2_node_48 = Stacked_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_48)
test_predict_Stacked_LSTM_Model_pos_y_2_node_48 = Stacked_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_48)
test_predict_Stacked_LSTM_Model_speed_2_node_48 = Stacked_LSTM_Model_speed.predict(X_testing_data_reshaped_node_48)
test_predict_Stacked_LSTM_Model_energy_2_node_48 = Stacked_LSTM_Model_energy.predict(X_testing_data_reshaped_node_48)

test_predict_CNN_LSTM_Model_pos_x_2_node_48 = CNN_LSTM_Model_pos_x.predict(X_testing_data_reshaped_cnn_node_48)
test_predict_CNN_LSTM_Model_pos_y_2_node_48 = CNN_LSTM_Model_pos_y.predict(X_testing_data_reshaped_cnn_node_48)
test_predict_CNN_LSTM_Model_speed_2_node_48 = CNN_LSTM_Model_speed.predict(X_testing_data_reshaped_cnn_node_48)
test_predict_CNN_LSTM_Model_energy_2_node_48 = CNN_LSTM_Model_energy.predict(X_testing_data_reshaped_cnn_node_48)

test_predict_LSTM_Model_pos_x_2_node_48 = LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_48)
test_predict_LSTM_Model_pos_y_2_node_48 = LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_48)
test_predict_LSTM_Model_speed_2_node_48 = LSTM_Model_speed.predict(X_testing_data_reshaped_node_48)
test_predict_LSTM_Model_energy_2_node_48 = LSTM_Model_energy.predict(X_testing_data_reshaped_node_48)

test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_48 = BiDirectonal_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_48)
test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_48 = BiDirectonal_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_48)
test_predict_BiDirectonal_LSTM_Model_speed_2_node_48 = BiDirectonal_LSTM_Model_speed.predict(X_testing_data_reshaped_node_48)
test_predict_BiDirectonal_LSTM_Model_energy_2_node_48 = BiDirectonal_LSTM_Model_energy.predict(X_testing_data_reshaped_node_48)

test_predict_GRU_Model_pos_x_2_node_48 = GRU_Model_pos_x.predict(X_testing_data_reshaped_node_48)
test_predict_GRU_Model_pos_y_2_node_48 = GRU_Model_pos_y.predict(X_testing_data_reshaped_node_48)
test_predict_GRU_Model_speed_2_node_48 = GRU_Model_speed.predict(X_testing_data_reshaped_node_48)
test_predict_GRU_Model_energy_2_node_48 = GRU_Model_energy.predict(X_testing_data_reshaped_node_48)

test_predict_RNN_Model_pos_x_2_node_48 = RNN_Model_pos_x.predict(X_testing_data_reshaped_node_48)
test_predict_RNN_Model_pos_y_2_node_48 = RNN_Model_pos_y.predict(X_testing_data_reshaped_node_48)
test_predict_RNN_Model_speed_2_node_48 = RNN_Model_speed.predict(X_testing_data_reshaped_node_48)
test_predict_RNN_Model_energy_2_node_48 = RNN_Model_energy.predict(X_testing_data_reshaped_node_48)

print("\n\n==================================================")
print("       PREDICITED POS X BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_pos_x_node_48)
plt.plot(test_predict_Stacked_LSTM_Model_pos_x_2_node_48)
plt.plot(test_predict_CNN_LSTM_Model_pos_x_2_node_48)
plt.plot(test_predict_LSTM_Model_pos_x_2_node_48)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_48)
plt.plot(test_predict_GRU_Model_pos_x_2_node_48)
plt.plot(test_predict_RNN_Model_pos_x_2_node_48)
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED POS Y BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_pos_y_node_48)
plt.plot(test_predict_Stacked_LSTM_Model_pos_y_2_node_48)
plt.plot(test_predict_CNN_LSTM_Model_pos_y_2_node_48)
plt.plot(test_predict_LSTM_Model_pos_y_2_node_48)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_48)
plt.plot(test_predict_GRU_Model_pos_y_2_node_48)
plt.plot(test_predict_RNN_Model_pos_y_2_node_48)
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED SPEED BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_speed_node_48)
plt.plot(test_predict_Stacked_LSTM_Model_speed_2_node_48)
plt.plot(test_predict_CNN_LSTM_Model_speed_2_node_48)
plt.plot(test_predict_LSTM_Model_speed_2_node_48)
plt.plot(test_predict_BiDirectonal_LSTM_Model_speed_2_node_48)
plt.plot(test_predict_GRU_Model_speed_2_node_48)
plt.plot(test_predict_RNN_Model_speed_2_node_48)
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED ENERGY BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_energy_node_48)
plt.plot(test_predict_Stacked_LSTM_Model_energy_2_node_48)
plt.plot(test_predict_CNN_LSTM_Model_energy_2_node_48)
plt.plot(test_predict_LSTM_Model_energy_2_node_48)
plt.plot(test_predict_BiDirectonal_LSTM_Model_energy_2_node_48)
plt.plot(test_predict_GRU_Model_energy_2_node_48)
plt.plot(test_predict_RNN_Model_energy_2_node_48)
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()

==================================================
       PREDICITED POS X BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED POS Y BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED SPEED BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED ENERGY BY ALL ALGORITHMS     
==================================================

print("\n\nROOT MEAN SQUARE OF ALL ALGORITHMS:")
print("====================================\n")

pretty_table_RMSE = PrettyTable()
pretty_table_RMSE.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])

pretty_table_RMSE.add_column("Pos X RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_Stacked_LSTM_Model_pos_x_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_CNN_LSTM_Model_pos_x_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_LSTM_Model_pos_x_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_GRU_Model_pos_x_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_RNN_Model_pos_x_2_node_48))),2)])

pretty_table_RMSE.add_column("Pos Y RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_Stacked_LSTM_Model_pos_y_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_CNN_LSTM_Model_pos_y_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_LSTM_Model_pos_y_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_GRU_Model_pos_y_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_RNN_Model_pos_y_2_node_48))),2)])

pretty_table_RMSE.add_column("Speed RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_Stacked_LSTM_Model_speed_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_CNN_LSTM_Model_speed_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_LSTM_Model_speed_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_BiDirectonal_LSTM_Model_speed_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_GRU_Model_speed_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_RNN_Model_speed_2_node_48))),2)])

pretty_table_RMSE.add_column("Energy RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_Stacked_LSTM_Model_energy_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_CNN_LSTM_Model_energy_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_LSTM_Model_energy_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_BiDirectonal_LSTM_Model_energy_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_GRU_Model_energy_2_node_48))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_RNN_Model_energy_2_node_48))),2)])

print(pretty_table_RMSE)

ROOT MEAN SQUARE OF ALL ALGORITHMS:
====================================

+-------------------+------------+------------+------------+-------------+
|     Algorithm     | Pos X RMSE | Pos Y RMSE | Speed RMSE | Energy RMSE |
+-------------------+------------+------------+------------+-------------+
|    Stacked_LSTM   |   171.57   |   123.87   |   374.98   |    70.27    |
|      CNN_LSTM     |   202.62   |   186.99   |   375.32   |    799.29   |
|        LSTM       |   166.31   |   163.37   |   375.26   |    72.43    |
| BiDirectonal_LSTM |   195.06   |   158.02   |   369.28   |   6430.81   |
|        GRU        |   181.21   |   178.45   |   375.2    |   6357.24   |
|        RNN        |   100.34   |   170.2    |   375.39   |    69.68    |
+-------------------+------------+------------+------------+-------------+

test_predict_Stacked_LSTM_Model_pos_x_2 = Stacked_LSTM_Model_pos_x.predict(X_testing_data_reshaped)
test_predict_Stacked_LSTM_Model_pos_y_2 = Stacked_LSTM_Model_pos_y.predict(X_testing_data_reshaped)
test_predict_Stacked_LSTM_Model_speed_2 = Stacked_LSTM_Model_speed.predict(X_testing_data_reshaped)
test_predict_Stacked_LSTM_Model_energy_2 = Stacked_LSTM_Model_energy.predict(X_testing_data_reshaped)

test_predict_CNN_LSTM_Model_pos_x_2 = CNN_LSTM_Model_pos_x.predict(X_testing_data_reshaped_cnn)
test_predict_CNN_LSTM_Model_pos_y_2 = CNN_LSTM_Model_pos_y.predict(X_testing_data_reshaped_cnn)
test_predict_CNN_LSTM_Model_speed_2 = CNN_LSTM_Model_speed.predict(X_testing_data_reshaped_cnn)
test_predict_CNN_LSTM_Model_energy_2 = CNN_LSTM_Model_energy.predict(X_testing_data_reshaped_cnn)

test_predict_LSTM_Model_pos_x_2 = LSTM_Model_pos_x.predict(X_testing_data_reshaped)
test_predict_LSTM_Model_pos_y_2 = LSTM_Model_pos_y.predict(X_testing_data_reshaped)
test_predict_LSTM_Model_speed_2 = LSTM_Model_speed.predict(X_testing_data_reshaped)
test_predict_LSTM_Model_energy_2 = LSTM_Model_energy.predict(X_testing_data_reshaped)

test_predict_BiDirectonal_LSTM_Model_pos_x_2 = BiDirectonal_LSTM_Model_pos_x.predict(X_testing_data_reshaped)
test_predict_BiDirectonal_LSTM_Model_pos_y_2 = BiDirectonal_LSTM_Model_pos_y.predict(X_testing_data_reshaped)
test_predict_BiDirectonal_LSTM_Model_speed_2 = BiDirectonal_LSTM_Model_speed.predict(X_testing_data_reshaped)
test_predict_BiDirectonal_LSTM_Model_energy_2 = BiDirectonal_LSTM_Model_energy.predict(X_testing_data_reshaped)

test_predict_GRU_Model_pos_x_2 = GRU_Model_pos_x.predict(X_testing_data_reshaped)
test_predict_GRU_Model_pos_y_2 = GRU_Model_pos_y.predict(X_testing_data_reshaped)
test_predict_GRU_Model_speed_2 = GRU_Model_speed.predict(X_testing_data_reshaped)
test_predict_GRU_Model_energy_2 = GRU_Model_energy.predict(X_testing_data_reshaped)

test_predict_RNN_Model_pos_x_2 = RNN_Model_pos_x.predict(X_testing_data_reshaped)
test_predict_RNN_Model_pos_y_2 = RNN_Model_pos_y.predict(X_testing_data_reshaped)
test_predict_RNN_Model_speed_2 = RNN_Model_speed.predict(X_testing_data_reshaped)
test_predict_RNN_Model_energy_2 = RNN_Model_energy.predict(X_testing_data_reshaped)

print("\n\n==================================================")
print("       PREDICITED POS X BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_pos_x)
plt.plot(test_predict_Stacked_LSTM_Model_pos_x_2)
plt.plot(test_predict_CNN_LSTM_Model_pos_x_2)
plt.plot(test_predict_LSTM_Model_pos_x_2)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_x_2)
plt.plot(test_predict_GRU_Model_pos_x_2)
plt.plot(test_predict_RNN_Model_pos_x_2)
plt.title('pos_x')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED POS Y BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_pos_y)
plt.plot(test_predict_Stacked_LSTM_Model_pos_y_2)
plt.plot(test_predict_CNN_LSTM_Model_pos_y_2)
plt.plot(test_predict_LSTM_Model_pos_y_2)
plt.plot(test_predict_BiDirectonal_LSTM_Model_pos_y_2)
plt.plot(test_predict_GRU_Model_pos_y_2)
plt.plot(test_predict_RNN_Model_pos_y_2)
plt.title('pos_y')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED SPEED BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_speed)
plt.plot(test_predict_Stacked_LSTM_Model_speed_2)
plt.plot(test_predict_CNN_LSTM_Model_speed_2)
plt.plot(test_predict_LSTM_Model_speed_2)
plt.plot(test_predict_BiDirectonal_LSTM_Model_speed_2)
plt.plot(test_predict_GRU_Model_speed_2)
plt.plot(test_predict_RNN_Model_speed_2)
plt.title('speed')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()


print("\n\n==================================================")
print("       PREDICITED ENERGY BY ALL ALGORITHMS     ")
print("==================================================\n\n")
plt.figure()
fig = plt.gcf()
fig.set_size_inches(15, 7)
plt.plot(y_testing_data_energy)
plt.plot(test_predict_Stacked_LSTM_Model_energy_2)
plt.plot(test_predict_CNN_LSTM_Model_energy_2)
plt.plot(test_predict_LSTM_Model_energy_2)
plt.plot(test_predict_BiDirectonal_LSTM_Model_energy_2)
plt.plot(test_predict_GRU_Model_energy_2)
plt.plot(test_predict_RNN_Model_energy_2)
plt.title('energy')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.legend(['Actual','Stacked_LSTM', "CNN_LSTM", "LSTM", "BiDirectonal_LSTM", "GRU", "RNN"], loc='upper right')
plt.show()

==================================================
       PREDICITED POS X BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED POS Y BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED SPEED BY ALL ALGORITHMS     
==================================================

==================================================
       PREDICITED ENERGY BY ALL ALGORITHMS     
==================================================

print("\n\nROOT MEAN SQUARE OF ALL ALGORITHMS:")
print("====================================\n")

pretty_table_RMSE = PrettyTable()
pretty_table_RMSE.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])

pretty_table_RMSE.add_column("Pos X RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_Stacked_LSTM_Model_pos_x_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_CNN_LSTM_Model_pos_x_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_LSTM_Model_pos_x_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_BiDirectonal_LSTM_Model_pos_x_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_GRU_Model_pos_x_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_RNN_Model_pos_x_2))),2)])

pretty_table_RMSE.add_column("Pos Y RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_Stacked_LSTM_Model_pos_y_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_CNN_LSTM_Model_pos_y_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_LSTM_Model_pos_y_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_BiDirectonal_LSTM_Model_pos_y_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_GRU_Model_pos_y_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_RNN_Model_pos_y_2))),2)])

pretty_table_RMSE.add_column("Speed RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_Stacked_LSTM_Model_speed_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_CNN_LSTM_Model_speed_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_LSTM_Model_speed_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_BiDirectonal_LSTM_Model_speed_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_GRU_Model_speed_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_RNN_Model_speed_2))),2)])

pretty_table_RMSE.add_column("Energy RMSE",[round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_Stacked_LSTM_Model_energy_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_CNN_LSTM_Model_energy_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_LSTM_Model_energy_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_BiDirectonal_LSTM_Model_energy_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_GRU_Model_energy_2))),2),
                                 round((math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_RNN_Model_energy_2))),2)])

print(pretty_table_RMSE)

ROOT MEAN SQUARE OF ALL ALGORITHMS:
====================================

+-------------------+------------+------------+------------+-------------+
|     Algorithm     | Pos X RMSE | Pos Y RMSE | Speed RMSE | Energy RMSE |
+-------------------+------------+------------+------------+-------------+
|    Stacked_LSTM   |   61.25    |   141.62   |   308.93   |    223.24   |
|      CNN_LSTM     |   102.17   |   111.84   |   308.73   |    723.94   |
|        LSTM       |   62.06    |   182.2    |   309.01   |    224.93   |
| BiDirectonal_LSTM |   21.31    |   207.42   |   307.37   |   4518.41   |
|        GRU        |   20.77    |   210.16   |   308.9    |   4254.63   |
|        RNN        |   140.28   |   190.02   |   308.97   |    222.78   |
+-------------------+------------+------------+------------+-------------+

====================================================================================

Bar Graph - RMSE of All Multilpe Models

====================================================================================

print("\n\n===============")
print("RMSE of Node 7: ")
print("===============\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_Stacked_LSTM_Model_pos_x_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_CNN_LSTM_Model_pos_x_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_LSTM_Model_pos_x_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_GRU_Model_pos_x_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_RNN_Model_pos_x_2_node_7)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_Stacked_LSTM_Model_pos_y_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_CNN_LSTM_Model_pos_y_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_LSTM_Model_pos_y_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_GRU_Model_pos_y_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_RNN_Model_pos_y_2_node_7)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_Stacked_LSTM_Model_speed_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_CNN_LSTM_Model_speed_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_LSTM_Model_speed_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_BiDirectonal_LSTM_Model_speed_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_GRU_Model_speed_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_RNN_Model_speed_2_node_7)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_Stacked_LSTM_Model_energy_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_CNN_LSTM_Model_energy_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_LSTM_Model_energy_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_BiDirectonal_LSTM_Model_energy_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_GRU_Model_energy_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_RNN_Model_energy_2_node_7)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.8)
ax.bar(X, data[1], color = 'purple', width = 0.6)
ax.bar(X, data[2], color = 'red', width = 0.4)
ax.bar(X, data[3], color = 'green', width = 0.2)
ax.legend(['POS X','POS Y','SPEED','ENERGY'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n===============")
print("RMSE of Node 15: ")
print("===============\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_Stacked_LSTM_Model_pos_x_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_CNN_LSTM_Model_pos_x_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_LSTM_Model_pos_x_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_GRU_Model_pos_x_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_RNN_Model_pos_x_2_node_15)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_Stacked_LSTM_Model_pos_y_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_CNN_LSTM_Model_pos_y_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_LSTM_Model_pos_y_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_GRU_Model_pos_y_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_RNN_Model_pos_y_2_node_15)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_Stacked_LSTM_Model_speed_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_CNN_LSTM_Model_speed_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_LSTM_Model_speed_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_BiDirectonal_LSTM_Model_speed_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_GRU_Model_speed_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_RNN_Model_speed_2_node_15)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_Stacked_LSTM_Model_energy_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_CNN_LSTM_Model_energy_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_LSTM_Model_energy_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_BiDirectonal_LSTM_Model_energy_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_GRU_Model_energy_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_RNN_Model_energy_2_node_15)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.8)
ax.bar(X, data[1], color = 'purple', width = 0.6)
ax.bar(X, data[2], color = 'red', width = 0.4)
ax.bar(X, data[3], color = 'green', width = 0.2)
ax.legend(['POS X','POS Y','SPEED','ENERGY'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n===============")
print("RMSE of Node 24: ")
print("===============\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_Stacked_LSTM_Model_pos_x_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_CNN_LSTM_Model_pos_x_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_LSTM_Model_pos_x_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_GRU_Model_pos_x_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_RNN_Model_pos_x_2_node_24)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_Stacked_LSTM_Model_pos_y_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_CNN_LSTM_Model_pos_y_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_LSTM_Model_pos_y_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_GRU_Model_pos_y_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_RNN_Model_pos_y_2_node_24)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_Stacked_LSTM_Model_speed_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_CNN_LSTM_Model_speed_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_LSTM_Model_speed_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_BiDirectonal_LSTM_Model_speed_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_GRU_Model_speed_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_RNN_Model_speed_2_node_24)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_Stacked_LSTM_Model_energy_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_CNN_LSTM_Model_energy_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_LSTM_Model_energy_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_BiDirectonal_LSTM_Model_energy_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_GRU_Model_energy_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_RNN_Model_energy_2_node_24)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.8)
ax.bar(X, data[1], color = 'purple', width = 0.6)
ax.bar(X, data[2], color = 'red', width = 0.4)
ax.bar(X, data[3], color = 'green', width = 0.2)
ax.legend(['POS X','POS Y','SPEED','ENERGY'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n===============")
print("RMSE of Node 33: ")
print("===============\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_Stacked_LSTM_Model_pos_x_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_CNN_LSTM_Model_pos_x_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_LSTM_Model_pos_x_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_GRU_Model_pos_x_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_RNN_Model_pos_x_2_node_33)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_Stacked_LSTM_Model_pos_y_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_CNN_LSTM_Model_pos_y_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_LSTM_Model_pos_y_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_GRU_Model_pos_y_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_RNN_Model_pos_y_2_node_33)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_Stacked_LSTM_Model_speed_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_CNN_LSTM_Model_speed_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_LSTM_Model_speed_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_BiDirectonal_LSTM_Model_speed_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_GRU_Model_speed_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_RNN_Model_speed_2_node_33)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_Stacked_LSTM_Model_energy_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_CNN_LSTM_Model_energy_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_LSTM_Model_energy_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_BiDirectonal_LSTM_Model_energy_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_GRU_Model_energy_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_RNN_Model_energy_2_node_33)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.8)
ax.bar(X, data[1], color = 'purple', width = 0.6)
ax.bar(X, data[2], color = 'red', width = 0.4)
ax.bar(X, data[3], color = 'green', width = 0.2)
ax.legend(['POS X','POS Y','SPEED','ENERGY'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n===============")
print("RMSE of Node 48: ")
print("===============\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_Stacked_LSTM_Model_pos_x_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_CNN_LSTM_Model_pos_x_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_LSTM_Model_pos_x_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_GRU_Model_pos_x_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_RNN_Model_pos_x_2_node_48)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_Stacked_LSTM_Model_pos_y_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_CNN_LSTM_Model_pos_y_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_LSTM_Model_pos_y_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_GRU_Model_pos_y_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_RNN_Model_pos_y_2_node_48)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_Stacked_LSTM_Model_speed_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_CNN_LSTM_Model_speed_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_LSTM_Model_speed_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_BiDirectonal_LSTM_Model_speed_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_GRU_Model_speed_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_RNN_Model_speed_2_node_48)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_Stacked_LSTM_Model_energy_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_CNN_LSTM_Model_energy_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_LSTM_Model_energy_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_BiDirectonal_LSTM_Model_energy_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_GRU_Model_energy_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_RNN_Model_energy_2_node_48)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.8)
ax.bar(X, data[1], color = 'purple', width = 0.6)
ax.bar(X, data[2], color = 'red', width = 0.4)
ax.bar(X, data[3], color = 'green', width = 0.2)
ax.legend(['POS X','POS Y','SPEED','ENERGY'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n===============")
print("RMSE of 18000 instances: ")
print("=====================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_Stacked_LSTM_Model_pos_x_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_CNN_LSTM_Model_pos_x_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_LSTM_Model_pos_x_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_BiDirectonal_LSTM_Model_pos_x_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_GRU_Model_pos_x_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_RNN_Model_pos_x_2)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_Stacked_LSTM_Model_pos_y_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_CNN_LSTM_Model_pos_y_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_LSTM_Model_pos_y_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_BiDirectonal_LSTM_Model_pos_y_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_GRU_Model_pos_y_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_RNN_Model_pos_y_2)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_Stacked_LSTM_Model_speed_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_CNN_LSTM_Model_speed_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_LSTM_Model_speed_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_BiDirectonal_LSTM_Model_speed_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_GRU_Model_speed_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_RNN_Model_speed_2)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_Stacked_LSTM_Model_energy_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_CNN_LSTM_Model_energy_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_LSTM_Model_energy_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_BiDirectonal_LSTM_Model_energy_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_GRU_Model_energy_2))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_RNN_Model_energy_2)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.8)
ax.bar(X, data[1], color = 'purple', width = 0.6)
ax.bar(X, data[2], color = 'red', width = 0.4)
ax.bar(X, data[3], color = 'green', width = 0.2)
ax.legend(['POS X','POS Y','SPEED','ENERGY'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

===============
RMSE of Node 7: 
===============

===============
RMSE of Node 15: 
===============

===============
RMSE of Node 24: 
===============

===============
RMSE of Node 33: 
===============

===============
RMSE of Node 48: 
===============

===============
RMSE of 18000 instances: 
=====================

User Input at Time T1

pos_x_input = input("\nPlease enter Pos X : ").strip()
pos_y_input = input("\nPlease enter Pos Y : ").strip()
speed_input = input("\nPlease enter Speed ").strip()
energy_input = input("\nPlease enter Energy : ").strip()

Please enter Pos X : 100

Please enter Pos Y : 100

Please enter Speed 100

Please enter Energy : 100

user_input = pd.DataFrame({ 'pos_x_input': [pos_x_input],'pos_y_input': [pos_y_input],'speed_input': [speed_input],'energy_input': [energy_input]})

print("\n\nUser Input Feature Vector:")
print("==========================\n")
print(user_input)

u=scaler.transform(np.array(user_input))
u_reshaped = u.reshape(u.shape[0],u.shape[1] , 1)
u_reshaped2 = u.reshape(u.shape[0],1,u.shape[1] , 1)

User Input Feature Vector:
==========================

  pos_x_input pos_y_input speed_input energy_input
0         100         100         100          100

Prediction By All Models

user_input_predict_Stacked_LSTM_Model_pos_x = Stacked_LSTM_Model_pos_x.predict(u_reshaped)
user_input_predict_CNN_LSTM_Model_pos_x = CNN_LSTM_Model_pos_x.predict(u_reshaped2)
user_input_predict_LSTM_Model_pos_x = LSTM_Model_pos_x.predict(u_reshaped)
user_input_predict_BiDirectonal_LSTM_Model_pos_x = BiDirectonal_LSTM_Model_pos_x.predict(u_reshaped)
user_input_predict_GRU_Model_pos_x = GRU_Model_pos_x.predict(u_reshaped)
user_input_predict_RNN_Model_pos_x = RNN_Model_pos_x.predict(u_reshaped)

user_input_predict_Stacked_LSTM_Model_pos_y = Stacked_LSTM_Model_pos_y.predict(u_reshaped)
user_input_predict_CNN_LSTM_Model_pos_y = CNN_LSTM_Model_pos_y.predict(u_reshaped2)
user_input_predict_LSTM_Model_pos_y = LSTM_Model_pos_y.predict(u_reshaped)
user_input_predict_BiDirectonal_LSTM_Model_pos_y = BiDirectonal_LSTM_Model_pos_y.predict(u_reshaped)
user_input_predict_GRU_Model_pos_y = GRU_Model_pos_y.predict(u_reshaped)
user_input_predict_RNN_Model_pos_y = RNN_Model_pos_y.predict(u_reshaped)

user_input_predict_Stacked_LSTM_Model_speed = Stacked_LSTM_Model_speed.predict(u_reshaped)
user_input_predict_CNN_LSTM_Model_speed = CNN_LSTM_Model_speed.predict(u_reshaped2)
user_input_predict_LSTM_Model_speed = LSTM_Model_speed.predict(u_reshaped)
user_input_predict_BiDirectonal_LSTM_Model_speed = BiDirectonal_LSTM_Model_speed.predict(u_reshaped)
user_input_predict_GRU_Model_speed = GRU_Model_speed.predict(u_reshaped)
user_input_predict_RNN_Model_speed = RNN_Model_speed.predict(u_reshaped)

user_input_predict_Stacked_LSTM_Model_energy = Stacked_LSTM_Model_energy.predict(u_reshaped)
user_input_predict_CNN_LSTM_Model_energy = CNN_LSTM_Model_energy.predict(u_reshaped2)
user_input_predict_LSTM_Model_energy = LSTM_Model_energy.predict(u_reshaped)
user_input_predict_BiDirectonal_LSTM_Model_energy = BiDirectonal_LSTM_Model_energy.predict(u_reshaped)
user_input_predict_GRU_Model_energy = GRU_Model_energy.predict(u_reshaped)
user_input_predict_RNN_Model_energy = RNN_Model_energy.predict(u_reshaped)

print("\n\nPredictions on User Input at T2:")
print("===============================\n")

pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Pos X",[user_input_predict_Stacked_LSTM_Model_pos_x[0][0],
                                 user_input_predict_CNN_LSTM_Model_pos_x[0][0],
                                 user_input_predict_LSTM_Model_pos_x[0][0],
                                 user_input_predict_BiDirectonal_LSTM_Model_pos_x[0][0],
                                 user_input_predict_GRU_Model_pos_x[0][0],
                                 user_input_predict_RNN_Model_pos_x[0][0]])

pretty_table.add_column("Pos Y",[user_input_predict_Stacked_LSTM_Model_pos_y[0][0],
                                 user_input_predict_CNN_LSTM_Model_pos_y[0][0],
                                 user_input_predict_LSTM_Model_pos_y[0][0],
                                 user_input_predict_BiDirectonal_LSTM_Model_pos_y[0][0],
                                 user_input_predict_GRU_Model_pos_y[0][0],
                                 user_input_predict_RNN_Model_pos_y[0][0]])

pretty_table.add_column("Speed",[user_input_predict_Stacked_LSTM_Model_speed[0][0],
                                 user_input_predict_CNN_LSTM_Model_speed[0][0],
                                 user_input_predict_LSTM_Model_speed[0][0],
                                 user_input_predict_BiDirectonal_LSTM_Model_speed[0][0],
                                 user_input_predict_GRU_Model_speed[0][0],
                                 user_input_predict_RNN_Model_speed[0][0]])

pretty_table.add_column("Energy",[user_input_predict_Stacked_LSTM_Model_energy[0][0],
                                 user_input_predict_CNN_LSTM_Model_energy[0][0],
                                 user_input_predict_LSTM_Model_energy[0][0],
                                 user_input_predict_BiDirectonal_LSTM_Model_energy[0][0],
                                 user_input_predict_GRU_Model_energy[0][0],
                                 user_input_predict_RNN_Model_energy[0][0]])
print(pretty_table)

Predictions on User Input at T2:
===============================

+-------------------+-----------+------------+-----------+------------+
|     Algorithm     |   Pos X   |   Pos Y    |   Speed   |   Energy   |
+-------------------+-----------+------------+-----------+------------+
|    Stacked_LSTM   | 354.88223 | 258.43912  | 11.563219 | 451.94415  |
|      CNN_LSTM     |  224.3265 | -298.5773  |  97.29312 | 6569.1597  |
|        LSTM       | 264.83844 | 317.49103  | 13.501372 |  454.1055  |
| BiDirectonal_LSTM | 32.326412 | 1017.68567 | 151.19135 | -549.58405 |
|        GRU        | 337.75198 | 302.61914  | 29.274237 | 1752.0741  |
|        RNN        |  282.0104 | -54.409695 | 13.382886 |  415.9577  |
+-------------------+-----------+------------+-----------+------------+

||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||

Visualze the Results

||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||

Single Models Vs Multiple Models

...........................................................................................

...........................................................................................

Node 7

======

print("\n\nNode 7 Pos X:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_pos_x_node_7,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.style.use('ggplot')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_x_node_7.predict(X_testing_data_reshaped_node_7),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_7),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_x_node_7.predict(X_testing_data_reshaped_cnn_node_7),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_x.predict(X_testing_data_reshaped_cnn_node_7),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_x_node_7.predict(X_testing_data_reshaped_node_7),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_7),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_x_node_7.predict(X_testing_data_reshaped_node_7),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_7),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_x_node_7.predict(X_testing_data_reshaped_node_7),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_x.predict(X_testing_data_reshaped_node_7),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_x_node_7.predict(X_testing_data_reshaped_node_7),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_x.predict(X_testing_data_reshaped_node_7),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

print("\n\nNode 7 Pos Y:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_pos_y_node_7,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_y_node_7.predict(X_testing_data_reshaped_node_7),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_7),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_y_node_7.predict(X_testing_data_reshaped_cnn_node_7),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_y.predict(X_testing_data_reshaped_cnn_node_7),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_y_node_7.predict(X_testing_data_reshaped_node_7),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_7),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_y_node_7.predict(X_testing_data_reshaped_node_7),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_7),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_y_node_7.predict(X_testing_data_reshaped_node_7),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_y.predict(X_testing_data_reshaped_node_7),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_y_node_7.predict(X_testing_data_reshaped_node_7),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_y.predict(X_testing_data_reshaped_node_7),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

print("\n\nNode 7 Speed:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_speed_node_7,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_speed_node_7.predict(X_testing_data_reshaped_node_7),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_speed.predict(X_testing_data_reshaped_node_7),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_speed_node_7.predict(X_testing_data_reshaped_cnn_node_7),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_speed.predict(X_testing_data_reshaped_cnn_node_7),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_speed_node_7.predict(X_testing_data_reshaped_node_7),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_speed.predict(X_testing_data_reshaped_node_7),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_speed_node_7.predict(X_testing_data_reshaped_node_7),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_speed.predict(X_testing_data_reshaped_node_7),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_speed_node_7.predict(X_testing_data_reshaped_node_7),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_speed.predict(X_testing_data_reshaped_node_7),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_speed_node_7.predict(X_testing_data_reshaped_node_7),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_speed.predict(X_testing_data_reshaped_node_7),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

print("\n\nNode 7 Energy:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_energy_node_7,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_energy_node_7.predict(X_testing_data_reshaped_node_7),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_energy.predict(X_testing_data_reshaped_node_7),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_energy_node_7.predict(X_testing_data_reshaped_cnn_node_7),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_energy.predict(X_testing_data_reshaped_cnn_node_7),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_energy_node_7.predict(X_testing_data_reshaped_node_7),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_energy.predict(X_testing_data_reshaped_node_7),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_energy_node_7.predict(X_testing_data_reshaped_node_7),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_energy.predict(X_testing_data_reshaped_node_7),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_energy_node_7.predict(X_testing_data_reshaped_node_7),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_energy.predict(X_testing_data_reshaped_node_7),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_energy_node_7.predict(X_testing_data_reshaped_node_7),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_energy.predict(X_testing_data_reshaped_node_7),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (jolues)')
plt.show()

Node 7 Pos X:
===============================

Node 7 Pos Y:
===============================

Node 7 Speed:
===============================

Node 7 Energy:
===============================

Node 15

=======

print("\n\nNode 15 Pos X:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_pos_x_node_15,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_x_node_15.predict(X_testing_data_reshaped_node_15),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_15),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_x_node_15.predict(X_testing_data_reshaped_cnn_node_15),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_x.predict(X_testing_data_reshaped_cnn_node_15),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_x_node_15.predict(X_testing_data_reshaped_node_15),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_15),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_x_node_15.predict(X_testing_data_reshaped_node_15),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_15),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_x_node_15.predict(X_testing_data_reshaped_node_15),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_x.predict(X_testing_data_reshaped_node_15),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_x_node_15.predict(X_testing_data_reshaped_node_15),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_x.predict(X_testing_data_reshaped_node_15),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

print("\n\nNode 15 Pos Y:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_pos_y_node_15,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_y_node_15.predict(X_testing_data_reshaped_node_15),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_15),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_y_node_15.predict(X_testing_data_reshaped_cnn_node_15),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_y.predict(X_testing_data_reshaped_cnn_node_15),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_y_node_15.predict(X_testing_data_reshaped_node_15),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_15),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_y_node_15.predict(X_testing_data_reshaped_node_15),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_15),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_y_node_15.predict(X_testing_data_reshaped_node_15),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_y.predict(X_testing_data_reshaped_node_15),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_y_node_15.predict(X_testing_data_reshaped_node_15),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_y.predict(X_testing_data_reshaped_node_15),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

print("\n\nNode 15 Speed:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_speed_node_15,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_speed_node_15.predict(X_testing_data_reshaped_node_15),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_speed.predict(X_testing_data_reshaped_node_15),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_speed_node_15.predict(X_testing_data_reshaped_cnn_node_15),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_speed.predict(X_testing_data_reshaped_cnn_node_15),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_speed_node_15.predict(X_testing_data_reshaped_node_15),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_speed.predict(X_testing_data_reshaped_node_15),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_speed_node_15.predict(X_testing_data_reshaped_node_15),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_speed.predict(X_testing_data_reshaped_node_15),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_speed_node_15.predict(X_testing_data_reshaped_node_15),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_speed.predict(X_testing_data_reshaped_node_15),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_speed_node_15.predict(X_testing_data_reshaped_node_15),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_speed.predict(X_testing_data_reshaped_node_15),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

print("\n\nNode 15 Energy:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_energy_node_15,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_energy_node_15.predict(X_testing_data_reshaped_node_15),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_energy.predict(X_testing_data_reshaped_node_15),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_energy_node_15.predict(X_testing_data_reshaped_cnn_node_15),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_energy.predict(X_testing_data_reshaped_cnn_node_15),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_energy_node_15.predict(X_testing_data_reshaped_node_15),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_energy.predict(X_testing_data_reshaped_node_15),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_energy_node_15.predict(X_testing_data_reshaped_node_15),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_energy.predict(X_testing_data_reshaped_node_15),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_energy_node_15.predict(X_testing_data_reshaped_node_15),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_energy.predict(X_testing_data_reshaped_node_15),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_energy_node_15.predict(X_testing_data_reshaped_node_15),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_energy.predict(X_testing_data_reshaped_node_15),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

Node 15 Pos X:
===============================

Node 15 Pos Y:
===============================

Node 15 Speed:
===============================

Node 15 Energy:
===============================

Node 24

=======

print("\n\nNode 24 Pos X:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_pos_x_node_24,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_x_node_24.predict(X_testing_data_reshaped_node_24),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_24),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_x_node_24.predict(X_testing_data_reshaped_cnn_node_24),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_x.predict(X_testing_data_reshaped_cnn_node_24),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_x_node_24.predict(X_testing_data_reshaped_node_24),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_24),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_x_node_24.predict(X_testing_data_reshaped_node_24),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_24),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_x_node_24.predict(X_testing_data_reshaped_node_24),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_x.predict(X_testing_data_reshaped_node_24),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_x_node_24.predict(X_testing_data_reshaped_node_24),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_x.predict(X_testing_data_reshaped_node_24),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

print("\n\nNode 24 Pos Y:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_pos_y_node_24,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_y_node_24.predict(X_testing_data_reshaped_node_24),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_24),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_y_node_24.predict(X_testing_data_reshaped_cnn_node_24),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_y.predict(X_testing_data_reshaped_cnn_node_24),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_y_node_24.predict(X_testing_data_reshaped_node_24),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_24),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_y_node_24.predict(X_testing_data_reshaped_node_24),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_24),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_y_node_24.predict(X_testing_data_reshaped_node_24),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_y.predict(X_testing_data_reshaped_node_24),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_y_node_24.predict(X_testing_data_reshaped_node_24),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_y.predict(X_testing_data_reshaped_node_24),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

print("\n\nNode 24 Speed:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_speed_node_24,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_speed_node_24.predict(X_testing_data_reshaped_node_24),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_speed.predict(X_testing_data_reshaped_node_24),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_speed_node_24.predict(X_testing_data_reshaped_cnn_node_24),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_speed.predict(X_testing_data_reshaped_cnn_node_24),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_speed_node_24.predict(X_testing_data_reshaped_node_24),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_speed.predict(X_testing_data_reshaped_node_24),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_speed_node_24.predict(X_testing_data_reshaped_node_24),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_speed.predict(X_testing_data_reshaped_node_24),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_speed_node_24.predict(X_testing_data_reshaped_node_24),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_speed.predict(X_testing_data_reshaped_node_24),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_speed_node_24.predict(X_testing_data_reshaped_node_24),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_speed.predict(X_testing_data_reshaped_node_24),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

print("\n\nNode 24 Energy:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_energy_node_24,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_energy_node_24.predict(X_testing_data_reshaped_node_24),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_energy.predict(X_testing_data_reshaped_node_24),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_energy_node_24.predict(X_testing_data_reshaped_cnn_node_24),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_energy.predict(X_testing_data_reshaped_cnn_node_24),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_energy_node_24.predict(X_testing_data_reshaped_node_24),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_energy.predict(X_testing_data_reshaped_node_24),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_energy_node_24.predict(X_testing_data_reshaped_node_24),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_energy.predict(X_testing_data_reshaped_node_24),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_energy_node_24.predict(X_testing_data_reshaped_node_24),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_energy.predict(X_testing_data_reshaped_node_24),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_energy_node_24.predict(X_testing_data_reshaped_node_24),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_energy.predict(X_testing_data_reshaped_node_24),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

Node 24 Pos X:
===============================

Node 24 Pos Y:
===============================

Node 24 Speed:
===============================

Node 24 Energy:
===============================

Node 33

=======

print("\n\nNode 33 Pos X:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_pos_x_node_33,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_x_node_33.predict(X_testing_data_reshaped_node_33),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_33),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_x_node_33.predict(X_testing_data_reshaped_cnn_node_33),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_x.predict(X_testing_data_reshaped_cnn_node_33),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_x_node_33.predict(X_testing_data_reshaped_node_33),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_33),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_x_node_33.predict(X_testing_data_reshaped_node_33),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_33),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_x_node_33.predict(X_testing_data_reshaped_node_33),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_x.predict(X_testing_data_reshaped_node_33),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_x_node_33.predict(X_testing_data_reshaped_node_33),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_x.predict(X_testing_data_reshaped_node_33),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

print("\n\nNode 33 Pos Y:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_pos_y_node_33,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_y_node_33.predict(X_testing_data_reshaped_node_33),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_33),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_y_node_33.predict(X_testing_data_reshaped_cnn_node_33),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_y.predict(X_testing_data_reshaped_cnn_node_33),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_y_node_33.predict(X_testing_data_reshaped_node_33),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_33),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_y_node_33.predict(X_testing_data_reshaped_node_33),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_33),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_y_node_33.predict(X_testing_data_reshaped_node_33),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_y.predict(X_testing_data_reshaped_node_33),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_y_node_33.predict(X_testing_data_reshaped_node_33),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_y.predict(X_testing_data_reshaped_node_33),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

print("\n\nNode 33 Speed:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_speed_node_33,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_speed_node_33.predict(X_testing_data_reshaped_node_33),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_speed.predict(X_testing_data_reshaped_node_33),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_speed_node_33.predict(X_testing_data_reshaped_cnn_node_33),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_speed.predict(X_testing_data_reshaped_cnn_node_33),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_speed_node_33.predict(X_testing_data_reshaped_node_33),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_speed.predict(X_testing_data_reshaped_node_33),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_speed_node_33.predict(X_testing_data_reshaped_node_33),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_speed.predict(X_testing_data_reshaped_node_33),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_speed_node_33.predict(X_testing_data_reshaped_node_33),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_speed.predict(X_testing_data_reshaped_node_33),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_speed_node_33.predict(X_testing_data_reshaped_node_33),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_speed.predict(X_testing_data_reshaped_node_33),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

print("\n\nNode 33 Energy:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_energy_node_33,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_energy_node_33.predict(X_testing_data_reshaped_node_33),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_energy.predict(X_testing_data_reshaped_node_33),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_energy_node_33.predict(X_testing_data_reshaped_cnn_node_33),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_energy.predict(X_testing_data_reshaped_cnn_node_33),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_energy_node_33.predict(X_testing_data_reshaped_node_33),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_energy.predict(X_testing_data_reshaped_node_33),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_energy_node_33.predict(X_testing_data_reshaped_node_33),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_energy.predict(X_testing_data_reshaped_node_33),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_energy_node_33.predict(X_testing_data_reshaped_node_33),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_energy.predict(X_testing_data_reshaped_node_33),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_energy_node_33.predict(X_testing_data_reshaped_node_33),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_energy.predict(X_testing_data_reshaped_node_33),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

Node 33 Pos X:
===============================

Node 33 Pos Y:
===============================

Node 33 Speed:
===============================

Node 33 Energy:
===============================

Node 48

=======

print("\n\nNode 48 Pos X:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_pos_x_node_48,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_x_node_48.predict(X_testing_data_reshaped_node_48),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_48),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_x_node_48.predict(X_testing_data_reshaped_cnn_node_48),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_x.predict(X_testing_data_reshaped_cnn_node_48),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_x_node_48.predict(X_testing_data_reshaped_node_48),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_48),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_x_node_48.predict(X_testing_data_reshaped_node_48),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_x.predict(X_testing_data_reshaped_node_48),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_x_node_48.predict(X_testing_data_reshaped_node_48),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_x.predict(X_testing_data_reshaped_node_48),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_x_node_48.predict(X_testing_data_reshaped_node_48),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_x.predict(X_testing_data_reshaped_node_48),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('X (meters)')
plt.show()

print("\n\nNode 48 Pos Y:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_pos_y_node_48,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_y_node_48.predict(X_testing_data_reshaped_node_48),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_48),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_y_node_48.predict(X_testing_data_reshaped_cnn_node_48),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_pos_y.predict(X_testing_data_reshaped_cnn_node_48),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_y_node_48.predict(X_testing_data_reshaped_node_48),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_48),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_y_node_48.predict(X_testing_data_reshaped_node_48),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_pos_y.predict(X_testing_data_reshaped_node_48),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_y_node_48.predict(X_testing_data_reshaped_node_48),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_pos_y.predict(X_testing_data_reshaped_node_48),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_y_node_48.predict(X_testing_data_reshaped_node_48),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_pos_y.predict(X_testing_data_reshaped_node_48),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Y (meters)')
plt.show()

print("\n\nNode 48 Speed:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_speed_node_48,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_speed_node_48.predict(X_testing_data_reshaped_node_48),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_speed.predict(X_testing_data_reshaped_node_48),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_speed_node_48.predict(X_testing_data_reshaped_cnn_node_48),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_speed.predict(X_testing_data_reshaped_cnn_node_48),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_speed_node_48.predict(X_testing_data_reshaped_node_48),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_speed.predict(X_testing_data_reshaped_node_48),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_speed_node_48.predict(X_testing_data_reshaped_node_48),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_speed.predict(X_testing_data_reshaped_node_48),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_speed_node_48.predict(X_testing_data_reshaped_node_48),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_speed.predict(X_testing_data_reshaped_node_48),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_speed_node_48.predict(X_testing_data_reshaped_node_48),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_speed.predict(X_testing_data_reshaped_node_48),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Speed (m/s)')
plt.show()

print("\n\nNode 48 Energy:")
print("===============================\n")

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(y_testing_data_energy_node_48,color="blue")
plt.legend(['True'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_energy_node_48.predict(X_testing_data_reshaped_node_48),color="red")
plt.legend(['Stacked_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(Stacked_LSTM_Model_energy.predict(X_testing_data_reshaped_node_48),color="red")
plt.legend(['Stacked_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_energy_node_48.predict(X_testing_data_reshaped_cnn_node_48),color="green")
plt.legend(['CNN_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(CNN_LSTM_Model_energy.predict(X_testing_data_reshaped_cnn_node_48),color="green")
plt.legend(['CNN_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_energy_node_48.predict(X_testing_data_reshaped_node_48),color="black")
plt.legend(['LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(LSTM_Model_energy.predict(X_testing_data_reshaped_node_48),color="black")
plt.legend(['LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_energy_node_48.predict(X_testing_data_reshaped_node_48),color="brown")
plt.legend(['BiDirectional_LSTM - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(BiDirectonal_LSTM_Model_energy.predict(X_testing_data_reshaped_node_48),color="brown")
plt.legend(['BiDirectional_LSTM - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_energy_node_48.predict(X_testing_data_reshaped_node_48),color="gray")
plt.legend(['GRU - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(GRU_Model_energy.predict(X_testing_data_reshaped_node_48),color="gray")
plt.legend(['GRU - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

###############################################################################
plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_energy_node_48.predict(X_testing_data_reshaped_node_48),color="magenta")
plt.legend(['RNN - Single'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

plt.figure()
fig = plt.gcf()
fig.set_size_inches(16, 1)
plt.plot(RNN_Model_energy.predict(X_testing_data_reshaped_node_48),color="magenta")
plt.legend(['RNN - Multiple'], loc='upper right')
plt.xlabel('Time (seconds)')
plt.ylabel('Energy (Joules)')
plt.show()

Node 48 Pos X:
===============================

Node 48 Pos Y:
===============================

Node 48 Speed:
===============================

Node 48 Energy:
===============================

print("\n\nRMSE of POS X for Node 7:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_Stacked_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_CNN_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_BiDirectonal_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_GRU_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_RNN_Model_pos_x))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_Stacked_LSTM_Model_pos_x_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_CNN_LSTM_Model_pos_x_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_LSTM_Model_pos_x_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_BiDirectonal_LSTM_Model_pos_x_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_GRU_Model_pos_x_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_RNN_Model_pos_x_node_7))])
print(pretty_table)

print("\n\nRMSE of POS Y for Node 7:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_Stacked_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_CNN_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_BiDirectonal_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_GRU_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_RNN_Model_pos_y))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_Stacked_LSTM_Model_pos_y_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_CNN_LSTM_Model_pos_y_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_LSTM_Model_pos_y_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_BiDirectonal_LSTM_Model_pos_y_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_GRU_Model_pos_y_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_RNN_Model_pos_y_node_7))])
print(pretty_table)

print("\n\nRMSE of Speed for Node 7:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_Stacked_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_CNN_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_BiDirectonal_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_GRU_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_RNN_Model_speed))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_Stacked_LSTM_Model_speed_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_CNN_LSTM_Model_speed_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_LSTM_Model_speed_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_BiDirectonal_LSTM_Model_speed_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_GRU_Model_speed_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_RNN_Model_speed_node_7))])
print(pretty_table)

print("\n\nRMSE of Energy for Node 7:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_Stacked_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_CNN_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_BiDirectonal_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_GRU_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_RNN_Model_energy))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_Stacked_LSTM_Model_energy_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_CNN_LSTM_Model_energy_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_LSTM_Model_energy_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_BiDirectonal_LSTM_Model_energy_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_GRU_Model_energy_node_7)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_RNN_Model_energy_node_7))])
print(pretty_table)

RMSE of POS X for Node 7:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 61.24921169192751  |  123.981724337066  |
|      CNN_LSTM     | 102.1710234948836  | 41.42521368851659  |
|        LSTM       | 62.06099552130979  | 122.62988736273873 |
| BiDirectonal_LSTM | 21.30604485598056  | 15.472769223108413 |
|        GRU        | 20.767906096783808 | 26.911247497909503 |
|        RNN        | 140.2831228889263  | 124.56495459719021 |
+-------------------+--------------------+--------------------+


RMSE of POS Y for Node 7:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 159.57752386657987 | 114.54259473021803 |
|      CNN_LSTM     | 133.44322081508946 | 53.92020967961218  |
|        LSTM       | 91.05439630731244  | 111.93091939923399 |
| BiDirectonal_LSTM | 28.416358116269265 | 70.12713281868652  |
|        GRU        | 23.35258700752008  | 79.34188876221245  |
|        RNN        | 66.37482678974489  | 114.53593711893676 |
+-------------------+--------------------+--------------------+


RMSE of Speed for Node 7:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 0.6647372753997914 | 1.3223860744926395 |
|      CNN_LSTM     | 1.1324576016620895 | 0.8392285797671369 |
|        LSTM       | 0.6249464855007287 | 0.6759420687072014 |
| BiDirectonal_LSTM | 3.4890517432098926 | 0.6367309253112398 |
|        GRU        | 0.6382154593351096 | 0.485575171241919  |
|        RNN        | 0.6192413369862964 | 0.4926025771755116 |
+-------------------+--------------------+--------------------+


RMSE of Energy for Node 7:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 580.9612708079775  |  59.6557895808515  |
|      CNN_LSTM     | 690.4185139473112  | 304.38738333529415 |
|        LSTM       |  580.793525264608  | 61.49070066779251  |
| BiDirectonal_LSTM | 4019.671459870819  | 196.12055188917748 |
|        GRU        | 3760.3388405168557 | 168.52778792856125 |
|        RNN        | 581.0078232728362  | 58.87792915288162  |
+-------------------+--------------------+--------------------+

print("\n\n==============================")
print("  RMSE of Node 7 ( pos x ): ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_Stacked_LSTM_Model_pos_x_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_CNN_LSTM_Model_pos_x_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_LSTM_Model_pos_x_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_BiDirectonal_LSTM_Model_pos_x_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_GRU_Model_pos_x_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_RNN_Model_pos_x_node_7)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_Stacked_LSTM_Model_pos_x_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_CNN_LSTM_Model_pos_x_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_LSTM_Model_pos_x_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_GRU_Model_pos_x_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_7,test_predict_RNN_Model_pos_x_2_node_7)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n==============================")
print("  RMSE of Node 7 ( pos y ): ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_Stacked_LSTM_Model_pos_y_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_CNN_LSTM_Model_pos_y_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_LSTM_Model_pos_y_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_BiDirectonal_LSTM_Model_pos_y_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_GRU_Model_pos_y_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_RNN_Model_pos_y_node_7)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_Stacked_LSTM_Model_pos_y_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_CNN_LSTM_Model_pos_y_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_LSTM_Model_pos_y_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_GRU_Model_pos_y_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_RNN_Model_pos_y_2_node_7)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n==============================")
print("  RMSE of Speed: ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_Stacked_LSTM_Model_speed_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_CNN_LSTM_Model_speed_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_LSTM_Model_speed_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_BiDirectonal_LSTM_Model_speed_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_GRU_Model_speed_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_RNN_Model_speed_node_7)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_Stacked_LSTM_Model_speed_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_CNN_LSTM_Model_speed_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_LSTM_Model_speed_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_BiDirectonal_LSTM_Model_speed_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_GRU_Model_speed_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_7,test_predict_RNN_Model_speed_2_node_7)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n==============================")
print("  RMSE of Energy: ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_Stacked_LSTM_Model_energy_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_CNN_LSTM_Model_energy_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_LSTM_Model_energy_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_BiDirectonal_LSTM_Model_energy_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_GRU_Model_energy_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_RNN_Model_energy_node_7)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_Stacked_LSTM_Model_energy_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_CNN_LSTM_Model_energy_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_LSTM_Model_energy_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_BiDirectonal_LSTM_Model_energy_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_GRU_Model_energy_2_node_7))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_7,test_predict_RNN_Model_energy_2_node_7)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

==============================
  RMSE of Node 7 ( pos x ): 
==============================

==============================
  RMSE of Node 7 ( pos y ): 
==============================

==============================
  RMSE of Speed: 
==============================

==============================
  RMSE of Energy: 
==============================

print("\n\nRMSE of POS X for Node 15:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_Stacked_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_CNN_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_BiDirectonal_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_GRU_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_RNN_Model_pos_x))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_Stacked_LSTM_Model_pos_x_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_CNN_LSTM_Model_pos_x_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_LSTM_Model_pos_x_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_BiDirectonal_LSTM_Model_pos_x_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_GRU_Model_pos_x_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_RNN_Model_pos_x_node_15))])
print(pretty_table)

print("\n\nRMSE of POS Y for Node 15:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_Stacked_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_CNN_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_BiDirectonal_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_GRU_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_RNN_Model_pos_y))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_Stacked_LSTM_Model_pos_y_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_CNN_LSTM_Model_pos_y_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_LSTM_Model_pos_y_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_BiDirectonal_LSTM_Model_pos_y_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_GRU_Model_pos_y_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_RNN_Model_pos_y_node_15))])
print(pretty_table)

print("\n\nRMSE of Speed for Node 15:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_Stacked_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_CNN_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_BiDirectonal_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_GRU_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_RNN_Model_speed))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_Stacked_LSTM_Model_speed_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_CNN_LSTM_Model_speed_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_LSTM_Model_speed_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_BiDirectonal_LSTM_Model_speed_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_GRU_Model_speed_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_RNN_Model_speed_node_15))])
print(pretty_table)

print("\n\nRMSE of Energy for Node 15:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_Stacked_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_CNN_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_BiDirectonal_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_GRU_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_RNN_Model_energy))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_Stacked_LSTM_Model_energy_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_CNN_LSTM_Model_energy_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_LSTM_Model_energy_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_BiDirectonal_LSTM_Model_energy_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_GRU_Model_energy_node_15)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_RNN_Model_energy_node_15))])
print(pretty_table)

RMSE of POS X for Node 15:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 61.24921169192751  | 145.97427322191535 |
|      CNN_LSTM     | 102.1710234948836  |  96.3507495509225  |
|        LSTM       | 62.06099552130979  | 143.80582473763488 |
| BiDirectonal_LSTM | 21.30604485598056  | 163.88808119833243 |
|        GRU        | 20.767906096783808 | 139.56143742628595 |
|        RNN        | 140.2831228889263  |  148.522614924966  |
+-------------------+--------------------+--------------------+


RMSE of POS Y for Node 15:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 159.57752386657987 | 176.9297653444743  |
|      CNN_LSTM     | 133.44322081508946 | 55.81996695241883  |
|        LSTM       | 91.05439630731244  | 173.89636892905497 |
| BiDirectonal_LSTM | 28.416358116269265 | 86.96190672294681  |
|        GRU        | 23.35258700752008  | 73.11046521732577  |
|        RNN        | 66.37482678974489  | 176.93451053857785 |
+-------------------+--------------------+--------------------+


RMSE of Speed for Node 15:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 0.6647372753997914 | 1.3345308098315403 |
|      CNN_LSTM     | 1.1324576016620895 | 1.785049553037206  |
|        LSTM       | 0.6249464855007287 | 0.7334628834121973 |
| BiDirectonal_LSTM | 3.4890517432098926 | 0.8147339061807343 |
|        GRU        | 0.6382154593351096 | 0.7858934747961992 |
|        RNN        | 0.6192413369862964 | 0.8584550146744845 |
+-------------------+--------------------+--------------------+


RMSE of Energy for Node 15:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 580.9612708079775  | 479.0988241247522  |
|      CNN_LSTM     | 690.4185139473112  | 119.44507918527674 |
|        LSTM       |  580.793525264608  | 478.41840458462974 |
| BiDirectonal_LSTM | 4019.671459870819  | 411.74089137786603 |
|        GRU        | 3760.3388405168557 | 255.74325590863873 |
|        RNN        | 581.0078232728362  | 479.5544453226019  |
+-------------------+--------------------+--------------------+

print("\n\n==============================")
print("  RMSE of Node 15 ( pos x ): ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_Stacked_LSTM_Model_pos_x_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_CNN_LSTM_Model_pos_x_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_LSTM_Model_pos_x_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_BiDirectonal_LSTM_Model_pos_x_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_GRU_Model_pos_x_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_RNN_Model_pos_x_node_15)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_Stacked_LSTM_Model_pos_x_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_CNN_LSTM_Model_pos_x_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_LSTM_Model_pos_x_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_GRU_Model_pos_x_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_15,test_predict_RNN_Model_pos_x_2_node_15)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n==============================")
print("  RMSE of Node 15 ( pos y ): ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_Stacked_LSTM_Model_pos_y_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_CNN_LSTM_Model_pos_y_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_LSTM_Model_pos_y_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_BiDirectonal_LSTM_Model_pos_y_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_GRU_Model_pos_y_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_RNN_Model_pos_y_node_15)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_Stacked_LSTM_Model_pos_y_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_CNN_LSTM_Model_pos_y_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_LSTM_Model_pos_y_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_GRU_Model_pos_y_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_15,test_predict_RNN_Model_pos_y_2_node_15)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n==============================")
print("  RMSE of Speed: ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_Stacked_LSTM_Model_speed_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_CNN_LSTM_Model_speed_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_LSTM_Model_speed_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_BiDirectonal_LSTM_Model_speed_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_GRU_Model_speed_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_RNN_Model_speed_node_15)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_Stacked_LSTM_Model_speed_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_CNN_LSTM_Model_speed_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_LSTM_Model_speed_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_BiDirectonal_LSTM_Model_speed_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_GRU_Model_speed_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_15,test_predict_RNN_Model_speed_2_node_15)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n==============================")
print("  RMSE of Energy: ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_Stacked_LSTM_Model_energy_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_CNN_LSTM_Model_energy_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_LSTM_Model_energy_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_BiDirectonal_LSTM_Model_energy_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_GRU_Model_energy_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_RNN_Model_energy_node_15)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_Stacked_LSTM_Model_energy_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_CNN_LSTM_Model_energy_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_LSTM_Model_energy_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_BiDirectonal_LSTM_Model_energy_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_GRU_Model_energy_2_node_15))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_15,test_predict_RNN_Model_energy_2_node_15)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

==============================
  RMSE of Node 15 ( pos x ): 
==============================

==============================
  RMSE of Node 15 ( pos y ): 
==============================

==============================
  RMSE of Speed: 
==============================

==============================
  RMSE of Energy: 
==============================

print("\n\nRMSE of POS X for Node 24:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_Stacked_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_CNN_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_BiDirectonal_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_GRU_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_RNN_Model_pos_x))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_Stacked_LSTM_Model_pos_x_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_CNN_LSTM_Model_pos_x_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_LSTM_Model_pos_x_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_BiDirectonal_LSTM_Model_pos_x_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_GRU_Model_pos_x_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_RNN_Model_pos_x_node_24))])
print(pretty_table)

print("\n\nRMSE of POS Y for Node 24:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_Stacked_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_CNN_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_BiDirectonal_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_GRU_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_RNN_Model_pos_y))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_y_node_24,test_predict_Stacked_LSTM_Model_pos_y_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_24,test_predict_CNN_LSTM_Model_pos_y_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_24,test_predict_LSTM_Model_pos_y_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_24,test_predict_BiDirectonal_LSTM_Model_pos_y_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_24,test_predict_GRU_Model_pos_y_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_24,test_predict_RNN_Model_pos_y_node_24))])
print(pretty_table)

print("\n\nRMSE of Speed for Node 24:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_Stacked_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_CNN_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_BiDirectonal_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_GRU_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_RNN_Model_speed))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_Stacked_LSTM_Model_speed_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_CNN_LSTM_Model_speed_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_LSTM_Model_speed_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_BiDirectonal_LSTM_Model_speed_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_GRU_Model_speed_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_RNN_Model_speed_node_24))])
print(pretty_table)

print("\n\nRMSE of Energy for Node 24:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_Stacked_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_CNN_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_BiDirectonal_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_GRU_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_RNN_Model_energy))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_Stacked_LSTM_Model_energy_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_CNN_LSTM_Model_energy_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_LSTM_Model_energy_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_BiDirectonal_LSTM_Model_energy_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_GRU_Model_energy_node_24)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_RNN_Model_energy_node_24))])
print(pretty_table)

RMSE of POS X for Node 24:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 61.24921169192751  | 257.7954130575904  |
|      CNN_LSTM     | 102.1710234948836  | 82.77935328590216  |
|        LSTM       | 62.06099552130979  | 255.82188337992102 |
| BiDirectonal_LSTM | 21.30604485598056  |  72.9606199636792  |
|        GRU        | 20.767906096783808 | 44.00216484194272  |
|        RNN        | 140.2831228889263  | 257.4535214800704  |
+-------------------+--------------------+--------------------+


RMSE of POS Y for Node 24:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 159.57752386657987 | 108.49681331079339 |
|      CNN_LSTM     | 133.44322081508946 | 94.94003132283116  |
|        LSTM       | 91.05439630731244  | 106.67321693285228 |
| BiDirectonal_LSTM | 28.416358116269265 | 25.28796170794887  |
|        GRU        | 23.35258700752008  |  85.3808500780627  |
|        RNN        | 66.37482678974489  | 109.4786457962932  |
+-------------------+--------------------+--------------------+


RMSE of Speed for Node 24:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 0.6647372753997914 | 2.1364596212758826 |
|      CNN_LSTM     | 1.1324576016620895 | 1.7924455355735254 |
|        LSTM       | 0.6249464855007287 | 1.2239059435773598 |
| BiDirectonal_LSTM | 3.4890517432098926 | 0.9237705686606663 |
|        GRU        | 0.6382154593351096 | 0.9231312058580767 |
|        RNN        | 0.6192413369862964 | 1.351143446594122  |
+-------------------+--------------------+--------------------+


RMSE of Energy for Node 24:
===============================

+-------------------+--------------------+-------------------+
|     Algorithm     |   Multiple Model   |    Single Model   |
+-------------------+--------------------+-------------------+
|    Stacked_LSTM   | 580.9612708079775  | 986.3790117496548 |
|      CNN_LSTM     | 690.4185139473112  | 845.9742692550271 |
|        LSTM       |  580.793525264608  | 984.2447765291922 |
| BiDirectonal_LSTM | 4019.671459870819  | 517.5964521813826 |
|        GRU        | 3760.3388405168557 | 679.3194368512528 |
|        RNN        | 581.0078232728362  | 987.4681164071391 |
+-------------------+--------------------+-------------------+

print("\n\n==============================")
print("  RMSE of Node 24 ( pos x ): ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_Stacked_LSTM_Model_pos_x_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_CNN_LSTM_Model_pos_x_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_LSTM_Model_pos_x_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_BiDirectonal_LSTM_Model_pos_x_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_GRU_Model_pos_x_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_RNN_Model_pos_x_node_24)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_Stacked_LSTM_Model_pos_x_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_CNN_LSTM_Model_pos_x_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_LSTM_Model_pos_x_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_GRU_Model_pos_x_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_24,test_predict_RNN_Model_pos_x_2_node_24)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n==============================")
print("  RMSE of Node 24 ( pos y ): ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_Stacked_LSTM_Model_pos_y_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_CNN_LSTM_Model_pos_y_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_LSTM_Model_pos_y_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_BiDirectonal_LSTM_Model_pos_y_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_GRU_Model_pos_y_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_RNN_Model_pos_y_node_24)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_Stacked_LSTM_Model_pos_y_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_CNN_LSTM_Model_pos_y_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_LSTM_Model_pos_y_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_GRU_Model_pos_y_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_7,test_predict_RNN_Model_pos_y_2_node_24)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n==============================")
print("  RMSE of Speed: ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_Stacked_LSTM_Model_speed_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_CNN_LSTM_Model_speed_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_LSTM_Model_speed_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_BiDirectonal_LSTM_Model_speed_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_GRU_Model_speed_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_RNN_Model_speed_node_24)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_Stacked_LSTM_Model_speed_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_CNN_LSTM_Model_speed_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_LSTM_Model_speed_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_BiDirectonal_LSTM_Model_speed_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_GRU_Model_speed_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_24,test_predict_RNN_Model_speed_2_node_24)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n==============================")
print("  RMSE of Energy: ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_Stacked_LSTM_Model_energy_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_CNN_LSTM_Model_energy_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_LSTM_Model_energy_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_BiDirectonal_LSTM_Model_energy_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_GRU_Model_energy_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_RNN_Model_energy_node_24)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_Stacked_LSTM_Model_energy_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_CNN_LSTM_Model_energy_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_LSTM_Model_energy_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_BiDirectonal_LSTM_Model_energy_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_GRU_Model_energy_2_node_24))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_24,test_predict_RNN_Model_energy_2_node_24)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

==============================
  RMSE of Node 24 ( pos x ): 
==============================

==============================
  RMSE of Node 24 ( pos y ): 
==============================

==============================
  RMSE of Speed: 
==============================

==============================
  RMSE of Energy: 
==============================

print("\n\nRMSE of POS X for Node 33:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_Stacked_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_CNN_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_BiDirectonal_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_GRU_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_RNN_Model_pos_x))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_Stacked_LSTM_Model_pos_x_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_CNN_LSTM_Model_pos_x_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_LSTM_Model_pos_x_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_BiDirectonal_LSTM_Model_pos_x_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_GRU_Model_pos_x_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_RNN_Model_pos_x_node_33))])
print(pretty_table)

print("\n\nRMSE of POS Y for Node 33:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_Stacked_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_CNN_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_BiDirectonal_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_GRU_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_RNN_Model_pos_y))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_Stacked_LSTM_Model_pos_y_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_CNN_LSTM_Model_pos_y_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_LSTM_Model_pos_y_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_BiDirectonal_LSTM_Model_pos_y_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_GRU_Model_pos_y_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_RNN_Model_pos_y_node_33))])
print(pretty_table)

print("\n\nRMSE of Speed for Node 33:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_Stacked_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_CNN_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_BiDirectonal_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_GRU_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_RNN_Model_speed))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_Stacked_LSTM_Model_speed_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_CNN_LSTM_Model_speed_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_LSTM_Model_speed_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_BiDirectonal_LSTM_Model_speed_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_GRU_Model_speed_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_RNN_Model_speed_node_33))])
print(pretty_table)

print("\n\nRMSE of Energy for Node 33:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_Stacked_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_CNN_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_BiDirectonal_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_GRU_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_RNN_Model_energy))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_Stacked_LSTM_Model_energy_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_CNN_LSTM_Model_energy_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_LSTM_Model_energy_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_BiDirectonal_LSTM_Model_energy_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_GRU_Model_energy_node_33)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_RNN_Model_energy_node_33))])
print(pretty_table)

RMSE of POS X for Node 33:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 61.24921169192751  | 193.70953735607617 |
|      CNN_LSTM     | 102.1710234948836  | 103.06990579867387 |
|        LSTM       | 62.06099552130979  | 191.86525172717202 |
| BiDirectonal_LSTM | 21.30604485598056  | 65.30544743297659  |
|        GRU        | 20.767906096783808 | 64.85719612818674  |
|        RNN        | 140.2831228889263  | 195.18939770976954 |
+-------------------+--------------------+--------------------+


RMSE of POS Y for Node 33:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 159.57752386657987 | 219.78996954108516 |
|      CNN_LSTM     | 133.44322081508946 | 83.60188222900314  |
|        LSTM       | 91.05439630731244  | 217.56895903489925 |
| BiDirectonal_LSTM | 28.416358116269265 | 73.44002737925149  |
|        GRU        | 23.35258700752008  | 91.72610847149676  |
|        RNN        | 66.37482678974489  | 220.59589685668757 |
+-------------------+--------------------+--------------------+


RMSE of Speed for Node 33:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 0.6647372753997914 | 0.8852174836354741 |
|      CNN_LSTM     | 1.1324576016620895 |  2.65029331668349  |
|        LSTM       | 0.6249464855007287 | 1.0731063914884176 |
| BiDirectonal_LSTM | 3.4890517432098926 | 1.4883888771416753 |
|        GRU        | 0.6382154593351096 | 0.8424116788231122 |
|        RNN        | 0.6192413369862964 | 0.8229388886971586 |
+-------------------+--------------------+--------------------+


RMSE of Energy for Node 33:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 580.9612708079775  | 476.3694606406331  |
|      CNN_LSTM     | 690.4185139473112  | 499.25925813945594 |
|        LSTM       |  580.793525264608  | 475.03147964115055 |
| BiDirectonal_LSTM | 4019.671459870819  | 544.7265719091582  |
|        GRU        | 3760.3388405168557 | 467.98088347075924 |
|        RNN        | 581.0078232728362  | 478.1609091476392  |
+-------------------+--------------------+--------------------+

print("\n\n==============================")
print("  RMSE of Node 33 ( pos x ): ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_Stacked_LSTM_Model_pos_x_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_CNN_LSTM_Model_pos_x_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_LSTM_Model_pos_x_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_BiDirectonal_LSTM_Model_pos_x_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_GRU_Model_pos_x_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_RNN_Model_pos_x_node_33)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_Stacked_LSTM_Model_pos_x_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_CNN_LSTM_Model_pos_x_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_LSTM_Model_pos_x_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_GRU_Model_pos_x_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_33,test_predict_RNN_Model_pos_x_2_node_33)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n==============================")
print("  RMSE of Node 33 ( pos y ): ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_Stacked_LSTM_Model_pos_y_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_CNN_LSTM_Model_pos_y_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_LSTM_Model_pos_y_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_BiDirectonal_LSTM_Model_pos_y_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_GRU_Model_pos_y_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_RNN_Model_pos_y_node_33)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_Stacked_LSTM_Model_pos_y_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_CNN_LSTM_Model_pos_y_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_LSTM_Model_pos_y_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_GRU_Model_pos_y_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_33,test_predict_RNN_Model_pos_y_2_node_33)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n==============================")
print("  RMSE of Speed: ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_Stacked_LSTM_Model_speed_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_CNN_LSTM_Model_speed_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_LSTM_Model_speed_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_BiDirectonal_LSTM_Model_speed_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_GRU_Model_speed_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_RNN_Model_speed_node_33)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_Stacked_LSTM_Model_speed_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_CNN_LSTM_Model_speed_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_LSTM_Model_speed_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_BiDirectonal_LSTM_Model_speed_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_GRU_Model_speed_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_33,test_predict_RNN_Model_speed_2_node_33)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n==============================")
print("  RMSE of Energy: ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_Stacked_LSTM_Model_energy_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_CNN_LSTM_Model_energy_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_LSTM_Model_energy_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_BiDirectonal_LSTM_Model_energy_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_GRU_Model_energy_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_RNN_Model_energy_node_33)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_Stacked_LSTM_Model_energy_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_CNN_LSTM_Model_energy_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_LSTM_Model_energy_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_BiDirectonal_LSTM_Model_energy_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_GRU_Model_energy_2_node_33))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_33,test_predict_RNN_Model_energy_2_node_33)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

==============================
  RMSE of Node 33 ( pos x ): 
==============================

==============================
  RMSE of Node 33 ( pos y ): 
==============================

==============================
  RMSE of Speed: 
==============================

==============================
  RMSE of Energy: 
==============================

print("\n\nRMSE of POS X for Node 48:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_Stacked_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_CNN_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_BiDirectonal_LSTM_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_GRU_Model_pos_x)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x,test_predict_RNN_Model_pos_x))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_Stacked_LSTM_Model_pos_x_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_CNN_LSTM_Model_pos_x_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_LSTM_Model_pos_x_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_BiDirectonal_LSTM_Model_pos_x_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_GRU_Model_pos_x_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_RNN_Model_pos_x_node_48))])
print(pretty_table)

print("\n\nRMSE of POS Y for Node 48:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_Stacked_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_CNN_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_BiDirectonal_LSTM_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_GRU_Model_pos_y)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y,test_predict_RNN_Model_pos_y))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_Stacked_LSTM_Model_pos_y_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_CNN_LSTM_Model_pos_y_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_LSTM_Model_pos_y_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_BiDirectonal_LSTM_Model_pos_y_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_GRU_Model_pos_y_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_RNN_Model_pos_y_node_48))])
print(pretty_table)

print("\n\nRMSE of Speed for Node 48:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_Stacked_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_CNN_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_BiDirectonal_LSTM_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_GRU_Model_speed)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed,test_predict_RNN_Model_speed))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_Stacked_LSTM_Model_speed_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_CNN_LSTM_Model_speed_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_LSTM_Model_speed_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_BiDirectonal_LSTM_Model_speed_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_GRU_Model_speed_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_RNN_Model_speed_node_48))])
print(pretty_table)

print("\n\nRMSE of Energy for Node 48:")
print("===============================\n")
pretty_table = PrettyTable()
pretty_table.add_column("Algorithm",["Stacked_LSTM","CNN_LSTM","LSTM","BiDirectonal_LSTM","GRU","RNN"])
pretty_table.add_column("Multiple Model",
                                [math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_Stacked_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_CNN_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_BiDirectonal_LSTM_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_GRU_Model_energy)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy,test_predict_RNN_Model_energy))])
pretty_table.add_column("Single Model",
                                [math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_Stacked_LSTM_Model_energy_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_CNN_LSTM_Model_energy_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_LSTM_Model_energy_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_BiDirectonal_LSTM_Model_energy_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_GRU_Model_energy_node_48)),
                                 math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_RNN_Model_energy_node_48))])
print(pretty_table)

RMSE of POS X for Node 48:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 61.24921169192751  | 320.46859908029677 |
|      CNN_LSTM     | 102.1710234948836  |  64.3659207800162  |
|        LSTM       | 62.06099552130979  | 319.9478090170709  |
| BiDirectonal_LSTM | 21.30604485598056  | 56.767080844719466 |
|        GRU        | 20.767906096783808 | 49.715648127865926 |
|        RNN        | 140.2831228889263  | 323.8269430504975  |
+-------------------+--------------------+--------------------+


RMSE of POS Y for Node 48:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 159.57752386657987 | 95.10228507476472  |
|      CNN_LSTM     | 133.44322081508946 | 20.353913128691545 |
|        LSTM       | 91.05439630731244  | 92.85477723599958  |
| BiDirectonal_LSTM | 28.416358116269265 | 7.633256587911894  |
|        GRU        | 23.35258700752008  | 6.476301148672023  |
|        RNN        | 66.37482678974489  | 97.86114465471238  |
+-------------------+--------------------+--------------------+


RMSE of Speed for Node 48:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 0.6647372753997914 | 2.4048618401773973 |
|      CNN_LSTM     | 1.1324576016620895 | 3.863205652102362  |
|        LSTM       | 0.6249464855007287 | 1.351553273418894  |
| BiDirectonal_LSTM | 3.4890517432098926 |  1.46665031821823  |
|        GRU        | 0.6382154593351096 | 1.4941851685138519 |
|        RNN        | 0.6192413369862964 | 1.6590009256306597 |
+-------------------+--------------------+--------------------+


RMSE of Energy for Node 48:
===============================

+-------------------+--------------------+--------------------+
|     Algorithm     |   Multiple Model   |    Single Model    |
+-------------------+--------------------+--------------------+
|    Stacked_LSTM   | 580.9612708079775  | 599.7573180351176  |
|      CNN_LSTM     | 690.4185139473112  | 1517.2697593171383 |
|        LSTM       |  580.793525264608  | 597.2554842870163  |
| BiDirectonal_LSTM | 4019.671459870819  | 1492.7014867622406 |
|        GRU        | 3760.3388405168557 | 1359.5611330777754 |
|        RNN        | 581.0078232728362  | 601.7859475573283  |
+-------------------+--------------------+--------------------+

print("\n\n==============================")
print("  RMSE of Node 48 ( pos x ): ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_Stacked_LSTM_Model_pos_x_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_CNN_LSTM_Model_pos_x_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_LSTM_Model_pos_x_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_BiDirectonal_LSTM_Model_pos_x_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_GRU_Model_pos_x_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_RNN_Model_pos_x_node_48)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_Stacked_LSTM_Model_pos_x_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_CNN_LSTM_Model_pos_x_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_LSTM_Model_pos_x_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_BiDirectonal_LSTM_Model_pos_x_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_GRU_Model_pos_x_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_x_node_48,test_predict_RNN_Model_pos_x_2_node_48)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n==============================")
print("  RMSE of Node 48 ( pos y ): ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_Stacked_LSTM_Model_pos_y_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_CNN_LSTM_Model_pos_y_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_LSTM_Model_pos_y_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_BiDirectonal_LSTM_Model_pos_y_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_GRU_Model_pos_y_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_RNN_Model_pos_y_node_48)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_Stacked_LSTM_Model_pos_y_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_CNN_LSTM_Model_pos_y_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_LSTM_Model_pos_y_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_BiDirectonal_LSTM_Model_pos_y_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_GRU_Model_pos_y_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_pos_y_node_48,test_predict_RNN_Model_pos_y_2_node_48)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n==============================")
print("  RMSE of Speed: ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_Stacked_LSTM_Model_speed_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_CNN_LSTM_Model_speed_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_LSTM_Model_speed_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_BiDirectonal_LSTM_Model_speed_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_GRU_Model_speed_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_RNN_Model_speed_node_48)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_Stacked_LSTM_Model_speed_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_CNN_LSTM_Model_speed_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_LSTM_Model_speed_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_BiDirectonal_LSTM_Model_speed_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_GRU_Model_speed_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_speed_node_48,test_predict_RNN_Model_speed_2_node_48)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

print("\n\n==============================")
print("  RMSE of Energy: ")
print("==============================\n\n")
data = [[(math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_Stacked_LSTM_Model_energy_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_CNN_LSTM_Model_energy_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_LSTM_Model_energy_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_BiDirectonal_LSTM_Model_energy_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_GRU_Model_energy_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_RNN_Model_energy_node_48)))],
        
        [(math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_Stacked_LSTM_Model_energy_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_CNN_LSTM_Model_energy_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_LSTM_Model_energy_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_BiDirectonal_LSTM_Model_energy_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_GRU_Model_energy_2_node_48))),
         (math.sqrt(mean_squared_error(y_testing_data_energy_node_48,test_predict_RNN_Model_energy_2_node_48)))]]

X = ['Stacked LSTM', 'CNN LSTM', 'LSTM', 'Bi-Directional LSTM', 'GRU','RNN']
fig = plt.figure()
fig.set_size_inches(10, 7)
ax = fig.add_axes([0,0,1,1])
ax.bar(X, data[0], color = 'blue', width = 0.4)
ax.bar(X, data[1], color = 'purple', width = 0.2)
ax.legend(['SINGLE MODEL','MULTIPLE MODEL'], loc='upper left')
plt.title('RMSE')
plt.xlabel('Algorithms')
plt.ylabel('Points')
plt.rc('grid', linestyle="--", color='gray')
plt.grid(True)
plt.show()

==============================
  RMSE of Node 48 ( pos x ): 
==============================

==============================
  RMSE of Node 48 ( pos y ): 
==============================

==============================
  RMSE of Speed: 
==============================

==============================
  RMSE of Energy: 
==============================

===============================================================

Thank you so much

===============================================================